Dataset generation for encoder training
By synthesizing CSI data to train CSI encoders, the approach addresses security risks in vendor data sharing, enabling secure and efficient training of CSI encoders in wireless communication systems.
Patent Information
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- QUALCOMM INC
- Filing Date
- 2024-11-08
- Publication Date
- 2026-05-15
AI Technical Summary
Existing wireless communication systems face challenges in securely and efficiently training CSI encoders due to the potential security risks associated with sharing proprietary vendor data during network entity collaboration.
A first network entity generates a synthesized set of CSI data from actual data collected from different vendors, which is then used to train a CSI encoder at a second network entity, ensuring the performance of the synthesized data meets specified thresholds, thus preventing access to proprietary information.
This approach enables secure and efficient training of CSI encoders, maintaining communication system integrity while ensuring performance similarity to actual vendor data without exposing sensitive information.
Smart Images

Figure CN2024130754_15052026_PF_FP_ABST
Abstract
Description
DATASET GENERATION FOR ENCODER TRAINING
[0001] FIELD OF TECHNOLOGY
[0002] The following relates to wireless communications, including dataset generation for encoder training.BACKGROUND
[0003] Wireless communications systems are widely deployed to provide various types of communication content such as voice, video, packet data, messaging, broadcast, and so on. These systems may be capable of supporting communication with multiple users by sharing the available system resources (e.g., time, frequency, and power) . Examples of such multiple-access systems include fourth generation (4G) systems such as Long Term Evolution (LTE) systems, LTE-Advanced (LTE-A) systems, or LTE-A Pro systems, and fifth generation (5G) systems which may be referred to as New Radio (NR) systems. These systems may employ technologies such as code division multiple access (CDMA) , time division multiple access (TDMA) , frequency division multiple access (FDMA) , orthogonal FDMA (OFDMA) , or discrete Fourier transform spread orthogonal frequency division multiplexing (DFT-S-OFDM) . A wireless multiple-access communications system may include one or more base stations, each supporting wireless communication for communication devices, which may be known as user equipment (UE) .SUMMARY
[0004] The systems, methods, and devices of this disclosure each have several innovative aspects, no single one of which is solely responsible for the desirable attributes disclosed herein.
[0005] A method for wireless communications by a first network entity is described. The method may include generating, at the first network entity, a first set of CS) data that is based on a second set of CSI data at the first network entity, the second set of CSI data being associated with a training of a first CSI decoder at the first network entity, where the first set of CSI data being a synthesized version of the second set of CSI data, outputting, to a second network entity, the first set of CSI data for training a first CSI encoder at the second network entity, and obtaining, from the second network entity, a first message based on outputting the first set of CSI data to the second network entity.
[0006] A first network entity for wireless communications is described. The first network entity may include one or more memories storing processor executable code, and one or more processors coupled with the one or more memories. The one or more processors may individually or collectively be operable to execute the code to cause the first network entity to generate, at the first network entity, a first set of CSI data that is based on a second set of CSI data at the first network entity, the second set of CSI data being associated with a training of a first CSI decoder at the first network entity, where the first set of CSI data being a synthesized version of the second set of CSI data, output, to a second network entity, the first set of CSI data for training a first CSI encoder at the second network entity, and obtain, from the second network entity, a first message based on outputting the first set of CSI data to the second network entity.
[0007] Another first network entity for wireless communications is described. The first network entity may include means for generating, at the first network entity, a first set of CSI data that is based on a second set of CSI data at the first network entity, the second set of CSI data being associated with a training of a first CSI decoder at the first network entity, where the first set of CSI data being a synthesized version of the second set of CSI data, means for outputting, to a second network entity, the first set of CSI data for training a first CSI encoder at the second network entity, and means for obtaining, from the second network entity, a first message based on outputting the first set of CSI data to the second network entity.
[0008] A non-transitory computer-readable medium storing code for wireless communications is described. The code may include instructions executable by one or more processors to generate, at the first network entity, a first set of CSI data that is based on a second set of CSI data at the first network entity, the second set of CSI data being associated with a training of a first CSI decoder at the first network entity, where the first set of CSI data being a synthesized version of the second set of CSI data, output, to a second network entity, the first set of CSI data for training a first CSI encoder at the second network entity, and obtain, from the second network entity, a first message based on outputting the first set of CSI data to the second network entity.
[0009] In some examples of the method, first network entities, and non-transitory computer-readable medium described herein, the second set of CSI data may be associated with a first performance indication that may be a function of a difference between the second set of CSI data and an output of a second CSI encoder at the first network entity and a second CSI decoder at the second network entity using the second set of CSI data.
[0010] In some examples of the method, first network entities, and non-transitory computer-readable medium described herein, the first set of CSI data may be associated with a second performance indication that may be a function of a difference between the first set of CSI data and an output of the second CSI encoder at the first network entity and the first CSI decoder at the first network entity using the first set of CSI data and generation of the first set of CSI data may be based on the second performance indication satisfying one or more thresholds.
[0011] In some examples of the method, first network entities, and non-transitory computer-readable medium described herein, generating the first set of CSI data may include operations, features, means, or instructions for generating, at the first network entity, the first set of CSI data based on the first set of CSI data satisfying a set of thresholds.
[0012] In some examples of the method, first network entities, and non-transitory computer-readable medium described herein, the set of thresholds may be key performance indicator thresholds.
[0013] In some examples of the method, first network entities, and non-transitory computer-readable medium described herein, a first quantity of CSI data samples within the first set of CSI data that satisfy the set of thresholds may be based on the second set of CSI data including a second quantity of CSI data samples that satisfy the set of thresholds.
[0014] In some examples of the method, first network entities, and non-transitory computer-readable medium described herein, the first set of CSI data includes a quantity of CSI data samples from a third set of CSI data.
[0015] In some examples of the method, first network entities, and non-transitory computer-readable medium described herein, the first set of CSI data includes the quantity of CSI data samples from the third set of CSI data based on the quantity of CSI data samples satisfying one or more respective threshold.
[0016] In some examples of the method, first network entities, and non-transitory computer-readable medium described herein, the first set of CSI data may be generated via a synthetic channel model, one or more random vectors, one or more random matrices, or any combination thereof.
[0017] A method for wireless communications by a second network entity is described. The method may include obtaining, from a first network entity, a set of parameters for a first CSI encoder at the first network entity and a set of information associated with an output of the first CSI encoder, the output of the first CSI encoder being based on a first set of CSI data at the first network entity, generating, at the second network entity and in response to reception of the set of parameters and the set of information, a second set of CSI data for training a second CSI encoder at the second network entity, the second set of CSI data being based on the first set of CSI data and being a synthesized version of the first set of CSI data, training, at the second network entity and in response to generation of the second set of CSI data, the second CSI encoder using the second set of CSI data, and outputting, to the first network entity, a first message that is obtained via the second CSI encoder based on training the second CSI encoder using the second set of CSI data.
[0018] A second network entity for wireless communications is described. The second network entity may include one or more memories storing processor executable code, and one or more processors coupled with the one or more memories. The one or more processors may individually or collectively be operable to execute the code to cause the second network entity to obtain, from a first network entity, a set of parameters for a first CSI encoder at the first network entity and a set of information associated with an output of the first CSI encoder, the output of the first CSI encoder being based on a first set of CSI data at the first network entity, generate, at the second network entity and in response to reception of the set of parameters and the set of information, a second set of CSI data for training a second CSI encoder at the second network entity, the second set of CSI data being based on the first set of CSI data and being a synthesized version of the first set of CSI data, training, at the second network entity and in response to generation of the second set of CSI data, the second CSI encoder used the second set of CSI data, and output, to the first network entity, a first message that is obtained via the second CSI encoder based on training the second CSI encoder using the second set of CSI data.
[0019] Another second network entity for wireless communications is described. The second network entity may include means for obtaining, from a first network entity, a set of parameters for a first CSI encoder at the first network entity and a set of information associated with an output of the first CSI encoder, the output of the first CSI encoder being based on a first set of CSI data at the first network entity, means for generating, at the second network entity and in response to reception of the set of parameters and the set of information, a second set of CSI data for training a second CSI encoder at the second network entity, the second set of CSI data being based on the first set of CSI data and being a synthesized version of the first set of CSI data, means for training, at the second network entity and in response to generation of the second set of CSI data, the second CSI encoder using the second set of CSI data, and means for outputting, to the first network entity, a first message that is obtained via the second CSI encoder based on training the second CSI encoder using the second set of CSI data.
[0020] A non-transitory computer-readable medium storing code for wireless communications is described. The code may include instructions executable by one or more processors to obtain, from a first network entity, a set of parameters for a first CSI encoder at the first network entity and a set of information associated with an output of the first CSI encoder, the output of the first CSI encoder being based on a first set of CSI data at the first network entity, generate, at the second network entity and in response to reception of the set of parameters and the set of information, a second set of CSI data for training a second CSI encoder at the second network entity, the second set of CSI data being based on the first set of CSI data and being a synthesized version of the first set of CSI data, training, at the second network entity and in response to generation of the second set of CSI data, the second CSI encoder used the second set of CSI data, and output, to the first network entity, a first message that is obtained via the second CSI encoder based on training the second CSI encoder using the second set of CSI data.
[0021] In some examples of the method, second network entities, and non-transitory computer-readable medium described herein, obtaining the set of information associated with the output of the first CSI encoder may include operations, features, means, or instructions for obtaining, from the first network entity for one or more data samples within the first set of CSI data, an indication of one or more outputs of the first CSI encoder using the first set of CSI data, an indication of statistical information associated with the one or more outputs of the first CSI encoder using the first set of CSI data, or a combination thereof.
[0022] In some examples of the method, second network entities, and non-transitory computer-readable medium described herein, generating the second set of CSI data may include operations, features, means, or instructions for generating a quantity of data samples that result in an output of the second CSI encoder being equal to the one or more outputs of the first CSI encoder using the first set of CSI data.
[0023] In some examples of the method, second network entities, and non-transitory computer-readable medium described herein, generating the second set of CSI data may include operations, features, means, or instructions for selecting a quantity of data samples for the second set of CSI data from a third set of CSI data based on the output of the second CSI encoder using the quantity of data samples from the third set of CSI data being equal to the one or more outputs of the first CSI encoder using the first set of CSI data.
[0024] In some examples of the method, second network entities, and non-transitory computer-readable medium described herein, the set of information associated with the output of the first CSI encoder may be obtained based on the output of a first CSI decoder at the first network entity using the first set of CSI data satisfying one or more thresholds.
[0025] In some examples of the method, second network entities, and non-transitory computer-readable medium described herein, the one or more thresholds may be key performance indicator thresholds.
[0026] In some examples of the method, second network entities, and non-transitory computer-readable medium described herein, the second set of CSI data may be generated via a synthetic channel model, one or more random vectors, one or more random matrices, or any combination thereof.
[0027] Details of one or more implementations of the subject matter described in this disclosure are set forth in the accompanying drawings and the description below. Other features, aspects, and advantages will become apparent from the description, the drawings, and the claims. Note that the relative dimensions of the following figures may not be drawn to scale.BRIEF DESCRIPTION OF THE DRAWINGS
[0028] FIG. 1 shows an example of a wireless communications system that supports dataset generation for encoder training in accordance with one or more aspects of the present disclosure.
[0029] FIG. 2 shows an example of a block diagram of an example machine learning (ML) model that supports dataset generation for encoder training in accordance with one or more aspects of the present disclosure.
[0030] FIG. 3 shows an example of a block diagram of an example ML architecture that supports dataset generation for encoder training in accordance with one or more aspects of the present disclosure.
[0031] FIG. 4 shows an example of a wireless communications system that supports dataset generation for encoder training in accordance with one or more aspects of the present disclosure.
[0032] FIGs. 5 and 6 show an example of a process flow that supports dataset generation for encoder training in accordance with one or more aspects of the present disclosure.
[0033] FIGs. 7 and 8 show block diagrams of devices that support dataset generation for encoder training in accordance with one or more aspects of the present disclosure.
[0034] FIG. 9 shows a block diagram of a communications manager that supports dataset generation for encoder training in accordance with one or more aspects of the present disclosure.
[0035] FIG. 10 shows a diagram of a system including a device that supports dataset generation for encoder training in accordance with one or more aspects of the present disclosure.
[0036] FIGs. 11 and 12 show block diagrams of devices that support dataset generation for encoder training in accordance with one or more aspects of the present disclosure.
[0037] FIG. 13 shows a block diagram of a communications manager that supports dataset generation for encoder training in accordance with one or more aspects of the present disclosure.
[0038] FIG. 14 shows a diagram of a system including a device that supports dataset generation for encoder training in accordance with one or more aspects of the present disclosure.
[0039] FIGs. 15 and 16 show flowcharts illustrating methods that support dataset generation for encoder training in accordance with one or more aspects of the present disclosure.DETAILED DESCRIPTION
[0040] In some communication systems, network entities may be configured with a codebook for channel state information (CSI) reporting. A network entity may use the codebook as a precoding matrix indicator (PMI) dictionary for reporting a PMI codework and to select a sequence of bits to report the PMI. In some examples, artificial intelligence (AI) or machine learning (ML) based CSI feedback may replace the codebook by implementing a CSI encoder to perform the operations of a PMI searching algorithm and a CSI decoder to perform the operations of the PMI codebook used to translate the CSI reporting bits to a PMI codeword. In some examples, network entities may collaborate on training an AI / ML model for the CSI encoder and decoder. In some cases, the training for both the encoder and the decoder at the respective network entities may occur at a single entity, the training may occur at the respective entities concurrently, or the training may occur at the respective entities sequentially. For example, when the training is separated and is sequential, a first network entity may first train a decoder and then share model information with a second network entity for the second network entity to train an encoder. In some cases, for the network side training, a network entity may collect data from various vendors (e.g., UE vendors, chip vendors, or both) and train a decoder on an aggregated set of data from the various vendors. However, sharing the dataset used at the network to specific network entities may result in potential security risks due to sharing proprietary information of the various different vendors.
[0041] The techniques of the present disclosure describes a network entity using a set of CSI data that is synthesized from another set of CSI data to train a CSI encoder thus preventing a network entity of a first vendor potentially having access to training data from other vendors. In some examples, a first network entity may generate a synthesized set of CSI dataset from an actual set of CSI data collected from different vendors. Further, the first network entity may transmit the synthesized set of CSI data to a second network entity for training a CSI encoder. In some other examples, the second network entity may receive a set of parameters for an encoder at the first network entity, information associated with an encoder output from the first network entity using the actual set of CSI data. Using the set of parameters and the information associated with an encoder output, the second network entity may generate the synthesized set of CSI data. Moreover, the first network entity or the second network entity may generate the synthesized set of CSI data such that the performance of the synthesized set of CSI data is relatively similar to the performance of the actual set of CSI data. For example, a set of data samples within the synthesized set of data may be generated or selected based on satisfying one or more thresholds. Therefore, the second network entity may be capable of training a CSI encoder using a synthesized set of CSI data that refrains from including vendor specific data and that performs similarly to the set of CSI data from various different vendors used at the first network entity. Thus, the techniques of the present disclosure may enable network entities the capability to train a CSI encoder in an effective and secure manner to ensure an efficient and secure wireless communication system.
[0042] Aspects of the disclosure are initially described in the context of wireless communications systems. Additional aspects of the disclosure are described with reference to a wireless communications system, a ML model diagram, a ML architecture diagram, and process flows. Aspects of the disclosure are further illustrated by and described with reference to apparatus diagrams, system diagrams, and flowcharts that relate to dataset generation for encoder training.
[0043] FIG. 1 shows an example of a wireless communications system 100 that supports dataset generation for encoder training in accordance with one or more aspects of the present disclosure. The wireless communications system 100 may include one or more devices, such as one or more network devices (e.g., network entities 105) , one or more UEs 115, and a core network 130. In some examples, the wireless communications system 100 may be a Long Term Evolution (LTE) network, an LTE-Advanced (LTE-A) network, an LTE-A Pro network, a New Radio (NR) network, or a network operating in accordance with other systems and radio technologies, including future systems and radio technologies not explicitly mentioned herein.
[0044] The network entities 105 may be dispersed throughout a geographic area to form the wireless communications system 100 and may include devices in different forms or having different capabilities. In various examples, a network entity 105 may be referred to as a network element, a mobility element, a radio access network (RAN) node, or network equipment, among other nomenclature. In some examples, network entities 105 and UEs 115 may wirelessly communicate via communication link (s) 125 (e.g., a radio frequency (RF) access link) . For example, a network entity 105 may support a coverage area 110 (e.g., a geographic coverage area) over which the UEs 115 and the network entity 105 may establish the communication link (s) 125. The coverage area 110 may be an example of a geographic area over which a network entity 105 and a UE 115 may support the communication of signals according to one or more radio access technologies (RATs) .
[0045] The UEs 115 may be dispersed throughout a coverage area 110 of the wireless communications system 100, and each UE 115 may be stationary, or mobile, or both at different times. The UEs 115 may be devices in different forms or having different capabilities. Some example UEs 115 are illustrated in FIG. 1. The UEs 115 described herein may be capable of supporting communications with various types of devices in the wireless communications system 100 (e.g., other wireless communication devices, including UEs 115 or network entities 105) , as shown in FIG. 1.
[0046] As described herein, a node of the wireless communications system 100, which may be referred to as a network node, or a wireless node, may be a network entity 105 (e.g., any network entity described herein) , a UE 115 (e.g., any UE described herein) , a network controller, an apparatus, a device, a computing system, one or more components, or another suitable processing entity configured to perform any of the techniques described herein. For example, a node may be a UE 115. As another example, a node may be a network entity 105. As another example, a first node may be configured to communicate with a second node or a third node. In one aspect of this example, the first node may be a UE 115, the second node may be a network entity 105, and the third node may be a UE 115. In another aspect of this example, the first node may be a UE 115, the second node may be a network entity 105, and the third node may be a network entity 105. In yet other aspects of this example, the first, second, and third nodes may be different relative to these examples. Similarly, reference to a UE 115, network entity 105, apparatus, device, computing system, or the like may include disclosure of the UE 115, network entity 105, apparatus, device, computing system, or the like being a node. For example, disclosure that a UE 115 is configured to receive information from a network entity 105 also discloses that a first node is configured to receive information from a second node.
[0047] In some examples, network entities 105 may communicate with a core network 130, or with one another, or both. For example, network entities 105 may communicate with the core network 130 via backhaul communication link (s) 120 (e.g., in accordance with an S1, N2, N3, or other interface protocol) . In some examples, network entities 105 may communicate with one another via backhaul communication link (s) 120 (e.g., in accordance with an X2, Xn, or other interface protocol) either directly (e.g., directly between network entities 105) or indirectly (e.g., via the core network 130) . In some examples, network entities 105 may communicate with one another via a midhaul communication link 162 (e.g., in accordance with a midhaul interface protocol) or a fronthaul communication link 168 (e.g., in accordance with a fronthaul interface protocol) , or any combination thereof. The backhaul communication link (s) 120, midhaul communication links 162, or fronthaul communication links 168 may be or include one or more wired links (e.g., an electrical link, an optical fiber link) or one or more wireless links (e.g., a radio link, a wireless optical link) , among other examples or various combinations thereof. A UE 115 may communicate with the core network 130 via a communication link 155.
[0048] One or more of the network entities 105 or network equipment described herein may include or may be referred to as a base station 140 (e.g., a base transceiver station, a radio base station, an NR base station, an access point, a radio transceiver, a NodeB, an eNodeB (eNB) , a next-generation NodeB or giga-NodeB (either of which may be referred to as a gNB) , a 5G NB, a next-generation eNB (ng-eNB) , a Home NodeB, a Home eNodeB, or other suitable terminology) . In some examples, a network entity 105 (e.g., a base station 140) may be implemented in an aggregated (e.g., monolithic, standalone) base station architecture, which may be configured to utilize a protocol stack that is physically or logically integrated within one network entity (e.g., a network entity 105 or a single RAN node, such as a base station 140) .
[0049] In some examples, a network entity 105 may be implemented in a disaggregated architecture (e.g., a disaggregated base station architecture, a disaggregated RAN architecture) , which may be configured to utilize a protocol stack that is physically or logically distributed among multiple network entities (e.g., network entities 105) , such as an integrated access and backhaul (IAB) network, an open RAN (O-RAN) (e.g., a network configuration sponsored by the O-RAN Alliance) , or a virtualized RAN (vRAN) (e.g., a cloud RAN (C-RAN) ) . For example, a network entity 105 may include one or more of a central unit (CU) , such as a CU 160, a distributed unit (DU) , such as a DU 165, a radio unit (RU) , such as an RU 170, a RAN Intelligent Controller (RIC) , such as an RIC 175 (e.g., a Near-Real Time RIC (Near-RT RIC) , a Non-Real Time RIC (Non-RT RIC) ) , a Service Management and Orchestration (SMO) system, such as an SMO system 180, or any combination thereof. An RU 170 may also be referred to as a radio head, a smart radio head, a remote radio head (RRH) , a remote radio unit (RRU) , or a transmission reception point (TRP) . One or more components of the network entities 105 in a disaggregated RAN architecture may be co-located, or one or more components of the network entities 105 may be located in distributed locations (e.g., separate physical locations) . In some examples, one or more of the network entities 105 of a disaggregated RAN architecture may be implemented as virtual units (e.g., a virtual CU (VCU) , a virtual DU (VDU) , a virtual RU (VRU) ) .
[0050] The split of functionality between a CU 160, a DU 165, and an RU 170 is flexible and may support different functionalities depending on which functions (e.g., network layer functions, protocol layer functions, baseband functions, RF functions, or any combinations thereof) are performed at a CU 160, a DU 165, or an RU 170. For example, a functional split of a protocol stack may be employed between a CU 160 and a DU 165 such that the CU 160 may support one or more layers of the protocol stack and the DU 165 may support one or more different layers of the protocol stack. In some examples, the CU 160 may host upper protocol layer (e.g., layer 3 (L3) , layer 2 (L2) ) functionality and signaling (e.g., Radio Resource Control (RRC) , service data adaptation protocol (SDAP) , Packet Data Convergence Protocol (PDCP) ) . The CU 160 (e.g., one or more CUs) may be connected to a DU 165 (e.g., one or more DUs) or an RU 170 (e.g., one or more RUs) , or some combination thereof, and the DUs 165, RUs 170, or both may host lower protocol layers, such as layer 1 (L1) (e.g., physical (PHY) layer) or L2 (e.g., radio link control (RLC) layer, medium access control (MAC) layer) functionality and signaling, and may each be at least partially controlled by the CU 160. Additionally, or alternatively, a functional split of the protocol stack may be employed between a DU 165 and an RU 170 such that the DU 165 may support one or more layers of the protocol stack and the RU 170 may support one or more different layers of the protocol stack. The DU 165 may support one or multiple different cells (e.g., via one or multiple different RUs, such as an RU 170) . In some cases, a functional split between a CU 160 and a DU 165 or between a DU 165 and an RU 170 may be within a protocol layer (e.g., some functions for a protocol layer may be performed by one of a CU 160, a DU 165, or an RU 170, while other functions of the protocol layer are performed by a different one of the CU 160, the DU 165, or the RU 170) . A CU 160 may be functionally split further into CU control plane (CU-CP) and CU user plane (CU-UP) functions. A CU 160 may be connected to a DU 165 via a midhaul communication link 162 (e.g., F1, F1-c, F1-u) , and a DU 165 may be connected to an RU 170 via a fronthaul communication link 168 (e.g., open fronthaul (FH) interface) . In some examples, a midhaul communication link 162 or a fronthaul communication link 168 may be implemented in accordance with an interface (e.g., a channel) between layers of a protocol stack supported by respective network entities (e.g., one or more of the network entities 105) that are in communication via such communication links.
[0051] In some wireless communications systems (e.g., the wireless communications system 100) , infrastructure and spectral resources for radio access may support wireless backhaul link capabilities to supplement wired backhaul connections, providing an IAB network architecture (e.g., to a core network 130) . In some cases, in an IAB network, one or more of the network entities 105 (e.g., network entities 105 or IAB node (s) 104) may be partially controlled by each other. The IAB node (s) 104 may be referred to as a donor entity or an IAB donor. A DU 165 or an RU 170 may be partially controlled by a CU 160 associated with a network entity 105 or base station 140 (such as a donor network entity or a donor base station) . The one or more donor entities (e.g., IAB donors) may be in communication with one or more additional devices (e.g., IAB node (s) 104) via supported access and backhaul links (e.g., backhaul communication link (s) 120) . IAB node (s) 104 may include an IAB mobile termination (IAB-MT) controlled (e.g., scheduled) by one or more DUs (e.g., DUs 165) of a coupled IAB donor. An IAB-MT may be equipped with an independent set of antennas for relay of communications with UEs 115 or may share the same antennas (e.g., of an RU 170) of IAB node (s) 104 used for access via the DU 165 of the IAB node (s) 104 (e.g., referred to as virtual IAB-MT (vIAB-MT) ) . In some examples, the IAB node (s) 104 may include one or more DUs (e.g., DUs 165) that support communication links with additional entities (e.g., IAB node (s) 104, UEs 115) within the relay chain or configuration of the access network (e.g., downstream) . In such cases, one or more components of the disaggregated RAN architecture (e.g., the IAB node (s) 104 or components of the IAB node (s) 104) may be configured to operate according to the techniques described herein.
[0052] In the case of the techniques described herein applied in the context of a disaggregated RAN architecture, one or more components of the disaggregated RAN architecture may be configured to support dataset generation for encoder training as described herein. For example, some operations described as being performed by a UE 115 or a network entity 105 (e.g., a base station 140) may additionally, or alternatively, be performed by one or more components of the disaggregated RAN architecture (e.g., components such as an IAB node, a DU 165, a CU 160, an RU 170, an RIC 175, an SMO system 180) .
[0053] A UE 115 may include or may be referred to as a mobile device, a wireless device, a remote device, a handheld device, or a subscriber device, or some other suitable terminology, where the “device” may also be referred to as a unit, a station, a terminal, or a client, among other examples. A UE 115 may also include or may be referred to as a personal electronic device such as a cellular phone, a personal digital assistant (PDA) , a tablet computer, a laptop computer, or a personal computer. In some examples, a UE 115 may include or be referred to as a wireless local loop (WLL) station, an Internet of Things (IoT) device, an Internet of Everything (IoE) device, or a machine type communications (MTC) device, among other examples, which may be implemented in various objects such as appliances, vehicles, or meters, among other examples.
[0054] The UEs 115 described herein may be able to communicate with various types of devices, such as UEs 115 that may sometimes operate as relays, as well as the network entities 105 and the network equipment including macro eNBs or gNBs, small cell eNBs or gNBs, or relay base stations, among other examples, as shown in FIG. 1.
[0055] The UEs 115 and the network entities 105 may wirelessly communicate with one another via the communication link (s) 125 (e.g., one or more access links) using resources associated with one or more carriers. The term “carrier” may refer to a set of RF spectrum resources having a defined PHY layer structure for supporting the communication link (s) 125. For example, a carrier used for the communication link (s) 125 may include a portion of an RF spectrum band (e.g., a bandwidth part (BWP) ) that is operated according to one or more PHY layer channels for a given RAT (e.g., LTE, LTE-A, LTE-A Pro, NR) . Each PHY layer channel may carry acquisition signaling (e.g., synchronization signals, system information) , control signaling that coordinates operation for the carrier, user data, or other signaling. The wireless communications system 100 may support communication with a UE 115 using carrier aggregation or multi-carrier operation. A UE 115 may be configured with multiple downlink component carriers and one or more uplink component carriers according to a carrier aggregation configuration. Carrier aggregation may be used with both frequency division duplexing (FDD) and time division duplexing (TDD) component carriers. Communication between a network entity 105 and other devices may refer to communication between the devices and any portion (e.g., entity, sub-entity) of a network entity 105. For example, the terms “transmitting, ” “receiving, ” or “communicating, ” when referring to a network entity 105, may refer to any portion of a network entity 105 (e.g., a base station 140, a CU 160, a DU 165, a RU 170) of a RAN communicating with another device (e.g., directly or via one or more other network entities, such as one or more of the network entities 105) .
[0056] Signal waveforms transmitted via a carrier may be made up of multiple subcarriers (e.g., using multi-carrier modulation (MCM) techniques such as orthogonal frequency division multiplexing (OFDM) or discrete Fourier transform spread OFDM (DFT-S-OFDM) ) . In a system employing MCM techniques, a resource element may refer to resources of one symbol period (e.g., a duration of one modulation symbol) and one subcarrier, in which case the symbol period and subcarrier spacing may be inversely related. The quantity of bits carried by each resource element may depend on the modulation scheme (e.g., the order of the modulation scheme, the coding rate of the modulation scheme, or both) , such that a relatively higher quantity of resource elements (e.g., in a transmission duration) and a relatively higher order of a modulation scheme may correspond to a relatively higher rate of communication. A wireless communications resource may refer to a combination of an RF spectrum resource, a time resource, and a spatial resource (e.g., a spatial layer, a beam) , and the use of multiple spatial resources may increase the data rate or data integrity for communications with a UE 115.
[0057] The time intervals for the network entities 105 or the UEs 115 may be expressed in multiples of a basic time unit which may, for example, refer to a sampling period of Ts=1 / (Δfmax·Nf) seconds, for which Δfmax may represent a supported subcarrier spacing, and Nf may represent a supported discrete Fourier transform (DFT) size. Time intervals of a communications resource may be organized according to radio frames each having a specified duration (e.g., 10 milliseconds (ms) ) . Each radio frame may be identified by a system frame number (SFN) (e.g., ranging from 0 to 1023) .
[0058] Each frame may include multiple consecutively-numbered subframes or slots, and each subframe or slot may have the same duration. In some examples, a frame may be divided (e.g., in the time domain) into subframes, and each subframe may be further divided into a quantity of slots. Alternatively, each frame may include a variable quantity of slots, and the quantity of slots may depend on subcarrier spacing. Each slot may include a quantity of symbol periods (e.g., depending on the length of the cyclic prefix prepended to each symbol period) . In some wireless communications systems, such as the wireless communications system 100, a slot may further be divided into multiple mini-slots associated with one or more symbols. Excluding the cyclic prefix, each symbol period may be associated with one or more (e.g., Nf) sampling periods.The duration of a symbol period may depend on the subcarrier spacing or frequency band of operation.
[0059] A subframe, a slot, a mini-slot, or a symbol may be the smallest scheduling unit (e.g., in the time domain) of the wireless communications system 100 and may be referred to as a transmission time interval (TTI) . In some examples, the TTI duration (e.g., a quantity of symbol periods in a TTI) may be variable. Additionally, or alternatively, the smallest scheduling unit of the wireless communications system 100 may be dynamically selected (e.g., in bursts of shortened TTIs (sTTIs) ) .
[0060] Physical channels may be multiplexed for communication using a carrier according to various techniques. A physical control channel and a physical data channel may be multiplexed for signaling via a downlink carrier, for example, using one or more of time division multiplexing (TDM) techniques, frequency division multiplexing (FDM) techniques, or hybrid TDM-FDM techniques. A control region (e.g., a control resource set (CORESET) ) for a physical control channel may be defined by a set of symbol periods and may extend across the system bandwidth or a subset of the system bandwidth of the carrier. One or more control regions (e.g., CORESETs) may be configured for a set of the UEs 115. For example, one or more of the UEs 115 may monitor or search control regions for control information according to one or more search space sets, and each search space set may include one or multiple control channel candidates in one or more aggregation levels arranged in a cascaded manner. An aggregation level for a control channel candidate may refer to an amount of control channel resources (e.g., control channel elements (CCEs) ) associated with encoded information for a control information format having a given payload size. Search space sets may include common search space sets configured for sending control information to UEs 115 (e.g., one or more UEs) or may include UE-specific search space sets for sending control information to a UE 115 (e.g., a specific UE) .
[0061] In some examples, a network entity 105 (e.g., a base station 140, an RU 170) may be movable and therefore provide communication coverage for a moving coverage area, such as the coverage area 110. In some examples, coverage areas 110 (e.g., different coverage areas) associated with different technologies may overlap, but the coverage areas 110 (e.g., different coverage areas) may be supported by the same network entity (e.g., a network entity 105) . In some other examples, overlapping coverage areas, such as a coverage area 110, associated with different technologies may be supported by different network entities (e.g., the network entities 105) . The wireless communications system 100 may include, for example, a heterogeneous network in which different types of the network entities 105 support communications for coverage areas 110 (e.g., different coverage areas) using the same or different RATs.
[0062] The wireless communications system 100 may support synchronous or asynchronous operation. For synchronous operation, network entities 105 (e.g., base stations 140) may have similar frame timings, and transmissions from different network entities (e.g., different ones of the network entities 105) may be approximately aligned in time. For asynchronous operation, network entities 105 may have different frame timings, and transmissions from different network entities (e.g., different ones of network entities 105) may, in some examples, not be aligned in time. The techniques described herein may be used for either synchronous or asynchronous operations.
[0063] Some UEs 115, such as MTC or IoT devices, may be relatively low cost or low complexity devices and may provide for automated communication between machines (e.g., via Machine-to-Machine (M2M) communication) . M2M communication or MTC may refer to data communication technologies that allow devices to communicate with one another or a network entity 105 (e.g., a base station 140) without human intervention. In some examples, M2M communication or MTC may include communications from devices that integrate sensors or meters to measure or capture information and relay such information to a central server or application program that uses the information or presents the information to humans interacting with the application program. Some UEs 115 may be designed to collect information or enable automated behavior of machines or other devices. Examples of applications for MTC devices include smart metering, inventory monitoring, water level monitoring, equipment monitoring, healthcare monitoring, wildlife monitoring, weather and geological event monitoring, fleet management and tracking, remote security sensing, physical access control, and transaction-based business charging.
[0064] The wireless communications system 100 may be configured to support ultra-reliable communications or low-latency communications, or various combinations thereof. For example, the wireless communications system 100 may be configured to support ultra-reliable low-latency communications (URLLC) . The UEs 115 may be designed to support ultra-reliable, low-latency, or critical functions. Ultra-reliable communications may include private communication or group communication and may be supported by one or more services such as push-to-talk, video, or data. Support for ultra-reliable, low-latency functions may include prioritization of services, and such services may be used for public safety or general commercial applications. The terms ultra-reliable, low-latency, and ultra-reliable low-latency may be used interchangeably herein.
[0065] In some examples, a UE 115 may be configured to support communicating directly with other UEs (e.g., one or more of the UEs 115) via a device-to-device (D2D) communication link, such as a D2D communication link 135 (e.g., in accordance with a peer-to-peer (P2P) , D2D, or sidelink protocol) . In some examples, one or more UEs 115 of a group that are performing D2D communications may be within the coverage area 110 of a network entity 105 (e.g., a base station 140, an RU 170) , which may support aspects of such D2D communications being configured by (e.g., scheduled by) the network entity 105. In some examples, one or more UEs 115 of such a group may be outside the coverage area 110 of a network entity 105 or may be otherwise unable to or not configured to receive transmissions from a network entity 105. In some examples, groups of the UEs 115 communicating via D2D communications may support a one-to-many (1: M) system in which each UE 115 transmits to one or more of the UEs 115 in the group. In some examples, a network entity 105 may facilitate the scheduling of resources for D2D communications. In some other examples, D2D communications may be carried out between the UEs 115 without an involvement of a network entity 105.
[0066] In some systems, a D2D communication link 135 may be an example of a communication channel, such as a sidelink communication channel, between vehicles (e.g., UEs 115) . In some examples, vehicles may communicate using vehicle-to- everything (V2X) communications, vehicle-to-vehicle (V2V) communications, or some combination of these. A vehicle may signal information related to traffic conditions, signal scheduling, weather, safety, emergencies, or any other information relevant to a V2X system. In some examples, vehicles in a V2X system may communicate with roadside infrastructure, such as roadside units, or with the network via one or more network nodes (e.g., network entities 105, base stations 140, RUs 170) using vehicle-to-network (V2N) communications, or with both.
[0067] The core network 130 may provide user authentication, access authorization, tracking, Internet Protocol (IP) connectivity, and other access, routing, or mobility functions. The core network 130 may be an evolved packet core (EPC) or 5G core (5GC) , which may include at least one control plane entity that manages access and mobility (e.g., a mobility management entity (MME) , an access and mobility management function (AMF) ) and at least one user plane entity that routes packets or interconnects to external networks (e.g., a serving gateway (S-GW) , a Packet Data Network (PDN) gateway (P-GW) , or a user plane function (UPF) ) . The control plane entity may manage non-access stratum (NAS) functions such as mobility, authentication, and bearer management for the UEs 115 served by the network entities 105 (e.g., base stations 140) associated with the core network 130. User IP packets may be transferred through the user plane entity, which may provide IP address allocation as well as other functions. The user plane entity may be connected to IP services 150 for one or more network operators. The IP services 150 may include access to the Internet, Intranet (s) , an IP Multimedia Subsystem (IMS) , or a Packet-Switched Streaming Service.
[0068] The wireless communications system 100 may operate using one or more frequency bands, which may be in the range of 300 megahertz (MHz) to 300 gigahertz (GHz) . Generally, the region from 300 MHz to 3 GHz is known as the ultra-high frequency (UHF) region or decimeter band because the wavelengths range from approximately one decimeter to one meter in length. UHF waves may be blocked or redirected by buildings and environmental features, which may be referred to as clusters, but the waves may penetrate structures sufficiently for a macro cell to provide service to the UEs 115 located indoors. Communications using UHF waves may be associated with smaller antennas and shorter ranges (e.g., less than one hundred kilometers) compared to communications using the smaller frequencies and longer waves of the high frequency (HF) or very high frequency (VHF) portion of the spectrum below 300 MHz.
[0069] The wireless communications system 100 may utilize both licensed and unlicensed RF spectrum bands. For example, the wireless communications system 100 may employ License Assisted Access (LAA) , LTE-Unlicensed (LTE-U) RAT, or NR technology using an unlicensed band such as the 5 GHz industrial, scientific, and medical (ISM) band. While operating using unlicensed RF spectrum bands, devices such as the network entities 105 and the UEs 115 may employ carrier sensing for collision detection and avoidance. In some examples, operations using unlicensed bands may be based on a carrier aggregation configuration in conjunction with component carriers operating using a licensed band (e.g., LAA) . Operations using unlicensed spectrum may include downlink transmissions, uplink transmissions, P2P transmissions, or D2D transmissions, among other examples.
[0070] A network entity 105 (e.g., a base station 140, an RU 170) or a UE 115 may be equipped with multiple antennas, which may be used to employ techniques such as transmit diversity, receive diversity, multiple-input multiple-output (MIMO) communications, or beamforming. The antennas of a network entity 105 or a UE 115 may be located within one or more antenna arrays or antenna panels, which may support MIMO operations or transmit or receive beamforming. For example, one or more base station antennas or antenna arrays may be co-located at an antenna assembly, such as an antenna tower. In some examples, antennas or antenna arrays associated with a network entity 105 may be located at diverse geographic locations. A network entity 105 may include an antenna array with a set of rows and columns of antenna ports that the network entity 105 may use to support beamforming of communications with a UE 115. Likewise, a UE 115 may include one or more antenna arrays that may support various MIMO or beamforming operations. Additionally, or alternatively, an antenna panel may support RF beamforming for a signal transmitted via an antenna port.
[0071] Beamforming, which may also be referred to as spatial filtering, directional transmission, or directional reception, is a signal processing technique that may be used at a transmitting device or a receiving device (e.g., a network entity 105, a UE 115) to shape or steer an antenna beam (e.g., a transmit beam, a receive beam) along a spatial path between the transmitting device and the receiving device. Beamforming may be achieved by combining the signals communicated via antenna elements of an antenna array such that some signals propagating along particular orientations with respect to an antenna array experience constructive interference while others experience destructive interference. The adjustment of signals communicated via the antenna elements may include a transmitting device or a receiving device applying amplitude offsets, phase offsets, or both to signals carried via the antenna elements associated with the device. The adjustments associated with each of the antenna elements may be defined by a beamforming weight set associated with a particular orientation (e.g., with respect to the antenna array of the transmitting device or receiving device, or with respect to some other orientation) .
[0072] A network entity 105 or a UE 115 may use beam sweeping techniques as part of beamforming operations. For example, a network entity 105 (e.g., a base station 140, an RU 170) may use multiple antennas or antenna arrays (e.g., antenna panels) to conduct beamforming operations for directional communications with a UE 115. Some signals (e.g., synchronization signals, reference signals, beam selection signals, or other control signals) may be transmitted by a network entity 105 multiple times along different directions. For example, the network entity 105 may transmit a signal according to different beamforming weight sets associated with different directions of transmission. Transmissions along different beam directions may be used to identify (e.g., by a transmitting device, such as a network entity 105, or by a receiving device, such as a UE 115) a beam direction for later transmission or reception by the network entity 105.
[0073] Some signals, such as data signals associated with a particular receiving device, may be transmitted by a transmitting device (e.g., a network entity 105 or a UE 115) along a single beam direction (e.g., a direction associated with the receiving device, such as another network entity 105 or UE 115) . In some examples, the beam direction associated with transmissions along a single beam direction may be determined based on a signal that was transmitted along one or more beam directions. For example, a UE 115 may receive one or more of the signals transmitted by the network entity 105 along different directions and may report to the network entity 105 an indication of the signal that the UE 115 received with a highest signal quality or an otherwise acceptable signal quality.
[0074] In some examples, transmissions by a device (e.g., by a network entity 105 or a UE 115) may be performed using multiple beam directions, and the device may use a combination of digital precoding or beamforming to generate a combined beam for transmission (e.g., from a network entity 105 to a UE 115) . The UE 115 may report feedback that indicates precoding weights for one or more beam directions, and the feedback may correspond to a configured set of beams across a system bandwidth or one or more sub-bands. The network entity 105 may transmit a reference signal (e.g., a cell-specific reference signal (CRS) , a channel state information reference signal (CSI-RS) ) , which may be precoded or unprecoded. The UE 115 may provide feedback for beam selection, which may be a precoding matrix indicator (PMI) or codebook-based feedback (e.g., a multi-panel type codebook, a linear combination type codebook, a port selection type codebook) . Although these techniques are described with reference to signals transmitted along one or more directions by a network entity 105 (e.g., a base station 140, an RU 170) , a UE 115 may employ similar techniques for transmitting signals multiple times along different directions (e.g., for identifying a beam direction for subsequent transmission or reception by the UE 115) or for transmitting a signal along a single direction (e.g., for transmitting data to a receiving device) .
[0075] A receiving device (e.g., a UE 115) may perform reception operations in accordance with multiple receive configurations (e.g., directional listening) when receiving various signals from a transmitting device (e.g., a network entity 105) , such as synchronization signals, reference signals, beam selection signals, or other control signals. For example, a receiving device may perform reception in accordance with multiple receive directions by receiving via different antenna subarrays, by processing received signals according to different antenna subarrays, by receiving according to different receive beamforming weight sets (e.g., different directional listening weight sets) applied to signals received at multiple antenna elements of an antenna array, or by processing received signals according to different receive beamforming weight sets applied to signals received at multiple antenna elements of an antenna array, any of which may be referred to as “listening” according to different receive configurations or receive directions. In some examples, a receiving device may use a single receive configuration to receive along a single beam direction (e.g., when receiving a data signal) . The single receive configuration may be aligned along a beam direction determined based on listening according to different receive configuration directions (e.g., a beam direction determined to have a highest signal strength, highest signal-to-noise ratio (SNR) , or otherwise acceptable signal quality based on listening according to multiple beam directions) .
[0076] The UEs 115 and the network entities 105 may support retransmissions of data to increase the likelihood that data is received successfully. Hybrid automatic repeat request (HARQ) feedback is one technique for increasing the likelihood that data is received correctly via a communication link (e.g., the communication link (s) 125, a D2D communication link 135) . HARQ may include a combination of error detection (e.g., using a cyclic redundancy check (CRC) ) , forward error correction (FEC) , and retransmission (e.g., automatic repeat request (ARQ) ) . HARQ may improve throughput at the MAC layer in relatively poor radio conditions (e.g., low signal-to-noise conditions) . In some examples, a device may support same-slot HARQ feedback, in which case the device may provide HARQ feedback in a specific slot for data received via a previous symbol in the slot. In some other examples, the device may provide HARQ feedback in a subsequent slot, or according to some other time interval.
[0077] Certain aspects and techniques as described herein may be implemented, at least in part, using an artificial intelligence (AI) program, such as a program that includes a machine learning (ML) or artificial neural network (ANN) model. An example ML model may include mathematical representations or define computing capabilities for making inferences from input data based on patterns or relationships identified in the input data. As used herein, the term “inferences” can include one or more of decisions, predictions, determinations, or values, which may represent outputs of the ML model. The computing capabilities may be defined in terms of certain parameters of the ML model, such as weights and biases. Weights may indicate relationships between certain input data and certain outputs of the ML model, and biases are offsets which may indicate a starting point for outputs of the ML model. An example ML model operating on input data may start at an initial output based on the biases and then update its output based on a combination of the input data and the weights.
[0078] In some aspects, an ML model may be configured to provide computing capabilities for wireless communications. Such an ML model may be configured with weights and biases to perform encoding and decoding of CSI feedback data to improve the efficiency of reporting CSI feedback. Thus, during operation of a device, the ML model may receive input data (e.g., raw channel data, channel pre-whitened data, an inference covariance matrix) and make inferences (e.g., inferences on CSI data to generate a latent message) based on the weights and biases.
[0079] ML models may be deployed in one or more devices (for example, network entities and user equipments (UEs) ) and may be configured to enhance various aspects of a wireless communication system. For example, an ML model may be trained to identify patterns or relationships in data corresponding to a network, a device, an air interface, or the like. An ML model may support operational decisions relating to one or more aspects associated with wireless communications devices, networks, or services. For example, an ML model may be utilized for supporting or improving aspects such as signal coding / decoding, network routing, energy conservation, transceiver circuitry controls, frequency synchronization, timing synchronization channel state estimation, channel equalization, channel state feedback, modulation, demodulation, device positioning, beamforming, load balancing, operations and management functions, security, etc.
[0080] ML models may be characterized in terms of types of learning that generate specific types of learned models that perform specific types of tasks. For example, different types of machine learning include supervised learning, unsupervised learning, semi-supervised learning, reinforcement learning, etc. ML models may be used to perform different tasks such as classification or regression, where classification refers to determining one or more discrete output values from a set of predefined output values, and regression refers to determining continuous values which are not bounded by predefined output values. Some example ML models configured for performing such tasks include ANNs such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs) , transformers, diffusion models, regression analysis models (such as statistical models) , large language models (LLMs) , decision tree learning (such as predictive models) , support vector networks (SVMs) , and probabilistic graphical models (such as a Bayesian network) , etc.
[0081] The description herein illustrates, by way of some examples, how one or more tasks or problems in wireless communications may benefit from the application of one or more ML models to replace the use of a codebook for CSI feedback reporting to improve the reporting of CSI feedback data. To facilitate the discussion, an ML model configured using an ANN is used, but it should be understood, that other types of ML models may be used instead of an ANN. Hence, unless expressly recited, subject matter regarding an ML model is not necessarily intended to be limited to an ANN solution. Further, it should be understood that, unless otherwise specifically stated, terms such “AI / ML model, ” “ML model, ” “trained ML model, ” “ANN, ” “model, ” “algorithm, ” or the like are intended to be interchangeable.
[0082] In some examples of the wireless communications system 100, network entities 105 may be configured with a codebook for CSI reporting. A network entity 105 may use the codebook as a PMI dictionary for reporting a PMI codework and to select a sequence of bits to report the PMI. In some examples, AI or ML based CSI feedback may replace the codebook by implementing a CSI encoder to take place of a PMI searching algorithm and a CSI decoder to take place of the PMI codebook used to translate the CSI reporting bits to a PMI codeword. In some examples, network entities 105 may collaborate on training an AI / ML model for the CSI encoder and decoder. In some cases, the training for both the encoder and the decoder at the respective network entities 105 may occur at a single device, the training may occur at the respective devices concurrently, or the training may occur at the respective devices sequentially. For example, when the training is separated and is sequential, a first network entity 105 (e.g., a network entity 105) may first train a decoder and then share model information with a second network entity 105 (e.g., a UE 115) for the second network entity 105 to train an encoder. In some cases, for the network side training, a network entity 105 may collect data from various vendors (e.g., UE 115 vendors, chip vendors, or both) and train a decoder on an aggregated set of data from the various vendors. However, sharing the dataset used at the network to specific network entities may result in potential security risks due to sharing proprietary information of the various different vendors.
[0083] The techniques of the present disclosure describes a network entity 105 using a set of CSI data that is synthesized from another set of CSI data to train a CSI encoder thus preventing a network entity 105 of a first vendor potentially having access to training data from other vendors. In some examples, a first network entity 105 may generate a synthesized set of CSI dataset from an actual set of CSI data collected from different vendors. Further, the first network entity 105 may transmit the synthesized set of CSI data to a second network entity 105 for training a CSI encoder. In some other examples, the second network entity 105 may receive a set of parameters for an encoder at the first network entity 105, information associated with an encoder output from the first network entity 105 using the actual set of CSI data. Using the set of parameters and the information associated with an encoder output, the second network entity 105 may generate the synthesized set of CSI data. Moreover, the first network entity 105 or the second network entity 105 may generate the synthesized set of CSI data such that the performance of the synthesized set of CSI data is relatively similar to the performance of the actual set of CSI data. For example, a set of data samples within the synthesized set of data may be generated or selected based on satisfying one or more thresholds. Therefore, the second network entity 105 may be capable of training a CSI encoder using a synthesized set of CSI data that refrains from including vendor specific data and that performs similarly to the set of CSI data from various different vendors used at the first network entity 105. Thus, the techniques of the present disclosure may enable network entities 105 the capability to train a CSI encoder in an effective and secure manner to ensure efficient and secure communications within the wireless communications system 100. Further descriptions of the techniques of the present disclosure may be described with reference to FIGs. 2 through 16.
[0084] FIG. 2 shows an example of a block diagram of an example machine learning (ML) model represented by an artificial neural network (ANN) 200 that supports dataset generation for encoder training in accordance with one or more aspects of the present disclosure.
[0085] ANN 200 may receive input data 206 which may include one or more bits of data 202, pre-processed data output from pre-processor 204 (optional) , or some combination thereof. Here, data 202 may include training data, verification data, application-related data, or the like, based, for example, on the stage of deployment of ANN 200. Pre-processor 204 may be included within ANN 200 in some other implementations. Pre-processor 204 may, for example, process all or a portion of data 202 which may result in some of data 202 being changed, replaced, deleted, etc. In some implementations, pre-processor 204 may add additional data to data 202. In some implementations, the pre-processor 204 may be a ML model, such as an ANN.
[0086] ANN 200 includes at least one first layer 208 of artificial neurons 210 to process input data 206 and provide resulting first layer data via connections or “edges” such as edges 212 to at least a portion of at least one second layer 214. Second layer 214 processes data received via edges 212 and provides second layer output data via edges 216 to at least a portion of at least one third layer 218. Third layer 218 processes data received via edges 216 and provides third layer output data via edges 220 to at least a portion of a final layer 222 including one or more neurons to provide output data 224. All or part of output data 224 may be further processed in some manner by (optional) post-processor 226. Thus, in certain examples, ANN 200 may provide output data 228 that is based on output data 224, post-processed data output from post-processor 226, or some combination thereof.
[0087] Post-processor 226 may be included within ANN 200 in some other implementations. Post-processor 226 may, for example, process all or a portion of output data 224 which may result in output data 228 being different, at least in part, to output data 224, as result of data being changed, replaced, deleted, etc. In some implementations, post-processor 226 may be configured to add additional data to output data 224. In this example, second layer 214 and third layer 218 represent intermediate or hidden layers that may be arranged in a hierarchical or other like structure. Although not explicitly shown, there may be one or more further intermediate layers between the second layer 214 and the third layer 218. In some implementations, the post-processor 226 may be a ML model, such as an ANN.
[0088] The structure and training of artificial neurons 210 in the various layers may be tailored to specific requirements of an application. Within a given layer such as first layer 208, second layer 214, or third layer 218 of ANN 200, some or all of the neurons may be configured to process information provided to the layer and output corresponding transformed information from the layer. For example, transformed information from a layer may represent a weighted sum of the input information associated with or otherwise based on a non-linear activation function or other activation function used to “activate” artificial neurons of a next layer. Artificial neurons in such a layer may be activated by or be responsive to parameters such as the previously described weights and biases of ANN 200. The weights and biases of ANN 200 may be adjusted during a training process or during operation of ANN 200. The weights of the various artificial neurons may control a strength of connections between layers or artificial neurons, while the biases may control a direction of connections between the layers or artificial neurons. An activation function may select or determine whether an artificial neuron transmits its output to the next layer or not in response to its received data.
[0089] Different activation functions may be used to model different types of non-linear relationships. By introducing non-linearity into an ML model, an activation function allows the configuration for the ML model to change in response to identifying or detecting complex patterns and relationships in the input data 206. Some non-exhaustive example activation functions include a sigmoid based activation function, a hyperbolic tangent (tanh) based activation function, a convolutional activation function, up-sampling, pooling, and a rectified linear unit (ReLU) based activation function.
[0090] Training of an ML model, such as ANN 200, may be conducted using training data. Training data may include one or more datasets which ANN 200 may use to identify patterns or relationships. Training data may represent various types of information, including written, visual, audio, environmental context, operational properties, etc. During training, the parameters (such as the weights and biases) of artificial neurons 210 may be changed, such as to minimize or otherwise reduce a loss function or a cost function. A training process may be repeated multiple times to fine-tune ANN 200 with each iteration.
[0091] Various ANN model structures are available for consideration. For example, in a feedforward ANN structure, each artificial neuron 210 in layer 214 receives information from the previous layer (such as, one or more artificial neurons 210 in layer 208) and produces information for the next layer (such as, one or more artificial neurons 210 in layer 218) . In a convolutional ANN structure, some layers may be organized into filters that extract features from data, such as the training data or the input data. In a recurrent ANN structure, some layers may have connections that allow for processing of data across time, such as for processing information having a temporal structure, such as time series data forecasting.
[0092] In an autoencoder ANN structure, compact representations of data may be processed and the model trained to predict or potentially reconstruct original data from a reduced set of features. An autoencoder ANN structure may be useful for tasks related to dimensionality reduction and data compression.
[0093] A generative adversarial ANN structure may include a generator ANN and a discriminator ANN that are trained to compete with each other. Generative-adversarial networks (GANs) are ANN structures that may be useful for tasks relating to generating synthetic data or improving the performance of other models.
[0094] A transformer ANN structure makes use of attention mechanisms that may enable the model to process input sequences in a parallel and efficient manner. An attention mechanism allows the model to focus on different parts of the input sequence at different times. Attention mechanisms may be implemented using a series of layers known as attention layers to compute weighted sums of input features based on a similarity between different elements of the input sequence. A transformer ANN structure may include a series of feedforward ANN layers whose configurations may change in response to identifying non-linear relationships between the input and output sequences, which may also be referred to as a process of “learning” by the ANN layers. The output of a transformer ANN structure may be obtained by applying a linear transformation to the output of a final attention layer. A transformer ANN structure may be of particular use for tasks that involve sequence modeling, or other like processing.
[0095] Another example type of ANN structure is a model with one or more invertible layers. Models of this type may be inverted or “unwrapped” to reveal the input data that was used to generate the output of a layer. Other example types of ANN model structures include fully connected neural networks (FCNNs) and long short-term memory (LSTM) networks.
[0096] ANN 200 or other ML models may be implemented in various types of processing circuits along with memory and applicable instructions therein. For example, general-purpose hardware circuits, such as, such as one or more central processing units (CPUs) , one or more graphics processing units (GPUs) , or suitable combinations thereof, may be employed to implement a model. In some implementations, one or more tensor processing units (TPUs) , neural processing units (NPUs) , or other special- purpose processors, field-programmable gate arrays (FPGAs) , application-specific integrated circuits (ASICs) , or the like may also be employed. In some implementations, the ML model may be implemented by a NPU or a TPU embedded in a system on chip (SoC) along with other components, such as one or more CPUs, GPUs, etc. A SoC includes several components manufactured on a shared semiconductor substrate. The NPU or TPU may be controlled by the one or more CPUs by configuring the ML model implemented by the NPU or TPU with weights and biases, providing certain training data to the ML model to configure the ML model, or providing input data to the ML model to obtain related inferences. The one or more CPUs may also receive the inferences and be configured to perform certain actions based on the inferences produced by the ML model. The actions performed by the one or more CPUs may include sending commands to other components of the SoC or components external to the SoC to perform certain actions. For example, the CPU may send commands to a RF transceiver based on the outputs or inferences obtained from an ML model to cause the RF transceiver to operate on a wireless network in accordance with the ML model.
[0097] In example aspects, an ML model may be trained prior to, or at some point following, operation of the ML model, such as ANN 200, on input data. When training the ML model, information in the form of applicable training data may be gathered or otherwise created for use in training an ANN accordingly. For example, training data may be gathered or otherwise created regarding information associated with received / transmitted signal strengths, interference, and resource usage data, as well as any other relevant data that might be useful for training a model to address one or more problems or issues in a communication system. In certain instances, all or part of the training data may originate in a user equipment (UE) or other device in a wireless communication system, or one or more network entities, or aggregated from multiple sources (such as a UE and a network entity / entities, one or more other UEs, the Internet, or the like) . In another example, training data may be generated or collected online, offline, or both online and offline by a UE, network entity, or other device (s) , and all or part of such training data may be transferred or shared (in real or near-real time) , such as through store and forward functions or the like. For example, one or more AI / ML models may be trained offline for a network entity 105 to train a CSI encoder in accordance with the techniques of the present disclosure.
[0098] Offline training may refer to creating and using a static training dataset, such as, in a batched manner, whereas online training may refer to a real-time collection and use of training data. For example, an ML model at a network device (such as, a UE) may be trained or fine-tuned using online or offline training. For offline training, data collection and training can occur in an offline manner at the network side (such as, at a base station or other network entity) or at the UE side. For online training, the training of a UE-side ML model may be performed locally at the UE or by a server device (such as, a server hosted by a UE vendor) in a real-time or near-real-time manner based on data provided to the server device from the UE. In certain instances, all or part of the training data may be shared within in a wireless communication system, or even shared (or obtained from) outside of the wireless communication system.
[0099] Once an ANN has been configured by setting parameters, including weights and biases, from training data, the ANN’s performance may be evaluated. In some scenarios, evaluation / verification tests may use a validation dataset, which may include data not in the training data, to compare the model’s performance to baseline or other benchmark information. The ANN configuration may be further refined, for example, by changing its architecture, re-training it on the data, or using different optimization techniques, etc.
[0100] In some implementations, one or more devices or services may support processes relating to a ML model’s usage, maintenance, activation, reporting, or the like. In certain instances, all or part of a dataset or model may be shared across multiple devices, to provide or otherwise augment or improve processing. In some examples, signaling mechanisms may be utilized at various nodes of wireless network to signal the capabilities for performing specific functions related to ML model, support for specific ML models, capabilities for gathering, creating, transmitting training data, or other ML related capabilities. ML models in wireless communication systems may, for example, be employed to support decisions or improve performance relating to wireless resource allocation or selection, wireless channel condition estimation, interference mitigation, beam management, positioning accuracy, energy savings, or modulation or coding schemes, etc. In some implementations, model deployment may occur jointly or separately at various network levels, such as, a UE, a network entity such as a base station, or a disaggregated network entity such as a central unit (CU) , a distributed unit (DU) , a radio unit (RU) , or the like.
[0101] In some examples, AI or ML based CSI feedback that utilize the ANN 200 may replace the codebook by implementing a CSI encoder to perform the operations of a PMI searching algorithm and a CSI decoder to perform the operations of the PMI codebook used to translate the CSI reporting bits to a PMI codeword. In some examples, network entities 105 may collaborate on training an AI / ML model (e.g., the ANN 200) for the CSI encoder and decoder. In some cases, the training for both the encoder and the decoder at the respective network entities 105 may occur at a single entity, the training may occur at the respective entities concurrently, or the training may occur at the respective entities sequentially. For example, when the training is separated and is sequential, a first network entity 105 (e.g., a network entity 105) may first train a decoder and then share model information with a second network entity 105 (e.g., a UE 115) for the second network entity 105 to train an encoder. In some cases, for the network side training, a network entity 105 may collect data from various vendors (e.g., UE 115 vendors, chip vendors, or both) and train a decoder on an aggregated set of data from the various vendors. However, sharing the dataset used at the network to specific network entities may result in potential security risks due to sharing proprietary information of the various different vendors.
[0102] The techniques of the present disclosure describes a network entity 105 using a set of CSI data that is synthesized from another set of CSI data to train a CSI encoder thus preventing a network entity 105 of a first vendor potentially having access to training data from other vendors. In some examples, a first network entity 105 may generate a synthesized set of CSI dataset from an actual set of CSI data collected from different vendors. In some other examples, the second network entity 105 may may generate a synthesized set of CSI dataset based on receiving a set of parameters for an encoder at the first network entity 105, information associated with an encoder output from the first network entity 105, or both where the first network entity 105 uses the actual set of CSI data. In some cases, after receiving or generating the synthesized set of CSI data, the second network entity 105 may then train a CSI encoder to generate one or more first messages. In some examples, the CSI encoder may include an AI / ML model such as the ANN 200. For example, the input data 202 for the AI / ML model of the CSI encoder at the second network entity 105 may include the synthesized set of CSI data and the output data 228 may include the latent messages generated by the CSI encoder.
[0103] Therefore, in accordance with the techniques of present disclosure, the second network entity 105 may be capable of training an AI / ML model (e.g., an ANN 200) of a CSI encoder using a synthesized set of CSI data that refrains from including vendor specific data and that performs similarly to the set of CSI data from various different vendors used at the first network entity 105. Thus, the techniques of the present disclosure may enable network entities 105 the capability to train a CSI encoder in an effective and secure manner to ensure efficient and secure communications within the wireless communications system 100. Further descriptions of the techniques of the present disclosure may be described with reference to FIGs. 3 through 16.
[0104] FIG. 3 shows an example of a block diagram of an ML architecture 300 that supports dataset generation for encoder training in accordance with one or more aspects of the present disclosure. In some examples, the ML architecture 300 may for a first wireless device 302 in communication a second wireless device 304. The first wireless device 302 may be configured for encoding and decoding CSI feedback data. Similarly, the second wireless device may be configured for encoding and decoding CSI feedback data. Note that the example ML architecture of first wireless device 302 may be applied to second wireless device 304, and vice versa.
[0105] First wireless device 302 may be, or may include, a chip, system on chip (SoC) , chipset, package or device that includes one or more processors, processing blocks or processing elements (collectively “processor 310” ) and one or more memory blocks or elements (collectively “memory 320” ) . Processor 310 may be coupled to transceiver 340, which includes radio frequency (RF) circuitry 342 coupled to antennas 346 via interface 344, for transmitting or receiving signals.
[0106] One or more ML models 330 (collectively “ML model 330” ) may be stored in memory 320 and accessible to processor (s) 310. Individual or groups of ML models 330 may be associated with respective model identifiers. In some aspects, different ML models 330, which may optionally be associated with different model identifiers, may have different characteristics. One or more ML models 330 may be selected based on respective features, characteristics, or applications, as well as characteristics or conditions of first wireless device 302 (such as, a power state, a mobility state, a battery reserve, a temperature, etc. ) . For example, ML models 330 may have different inference data and output pairings (such as, different types of inference data produce different types of output) , different levels of accuracies associated with the predictions, different latencies associated with producing the predictions, different ML model sizes, different coefficients, different parameters, etc.
[0107] Processor 310 may deploy ML models 330 to produce respective output data based on input data. The input data may include, for example, raw channel data, channel pre-whitened data, inference covariance matrices, or any combination thereof. The output data may include, for example, a latent message which may be used as an input to a CSI decoder. The output data of the CSI decoder may include, for example, a downlink channel matrix, a transmission covariance matrix, downlink precoders, an inference covariance matrix, raw downlink channel data, whitened downlink channel data, or any combination thereof.
[0108] In some aspects, model server 350 may perform various ML management tasks for first wireless device 302 and / or second wireless device 304. For example, model server 350 may host various types and / or versions of ML models 330 for first wireless device 302 and / or second wireless device 304 to download. Model server 350 may monitor and evaluate the performance of ML model 330. Model server 350 may switch to a different ML model 350 being used at first wireless device 302 or second wireless device 304, and model server 350 may provide such an instruction to the respective first wireless device 302 or second wireless device 304. Model server 350 may operate as a model training host and update ML model 330 using training data. In some cases, the model server 350 may operate as a data source to collect and host training data, inference data, performance feedback, etc., associated with ML model 330.
[0109] In some examples, AI or ML based CSI feedback that utilizes the ML architecture 300 may replace the codebook by implementing a CSI encoder to perform the operations of a PMI searching algorithm and a CSI decoder to perform the operations of the PMI codebook used to translate the CSI reporting bits to a PMI codeword. In some examples, network entities 105 may collaborate on training an AI / ML model (e.g., an AI / ML model utilizing the ML architecture 300) for the CSI encoder and decoder. In some cases, the training for both the encoder and the decoder at the respective network entities 105 may occur at a single entity, the training may occur at the respective entities concurrently, or the training may occur at the respective entities sequentially. For example, when the training is separated and is sequential, a first network entity 105 (e.g., a network entity 105) may first train a decoder and then share model information with a second network entity 105 (e.g., a UE 115) for the second network entity 105 to train an encoder. In some cases, for the network side training, a network entity 105 may collect data from various vendors (e.g., UE 115 vendors, chip vendors, or both) and train a decoder on an aggregated set of data from the various vendors. However, sharing the dataset used at the network to specific network entities may result in potential security risks due to sharing proprietary information of the various different vendors.
[0110] The techniques of the present disclosure describes a network entity 105 using a set of CSI data that is synthesized from another set of CSI data to train a CSI encoder thus preventing a network entity 105 of a first vendor potentially having access to training data from other vendors. In some examples, a first network entity 105 may generate a synthesized set of CSI dataset from an actual set of CSI data collected from different vendors. In some other examples, the second network entity 105 may may generate a synthesized set of CSI dataset based on receiving a set of parameters for an encoder at the first network entity 105, information associated with an encoder output from the first network entity 105, or both where the first network entity 105 uses the actual set of CSI data. In some cases, after receiving or generating the synthesized set of CSI data, the second network entity 105 may then train a CSI encoder to generate one or more first messages. In some examples, the CSI encoder may include an AI / ML model. For example, the input data for the AI / ML model of the CSI encoder at the second network entity 105 may include the synthesized set of CSI data and the output data may include the latent messages generated by the CSI encoder.
[0111] Therefore, in accordance with the techniques of present disclosure, the second network entity 105 may be capable of training an AI / ML model (e.g., an AI / ML model utilizing the ML architecture 300) of a CSI encoder using a synthesized set of CSI data that refrains from including vendor specific data and that performs similarly to the set of CSI data from various different vendors used at the first network entity 105. Thus, the techniques of the present disclosure may enable network entities 105 the capability to train a CSI encoder in an effective and secure manner to ensure efficient and secure communications within the wireless communications system 100. Further descriptions of the techniques of the present disclosure may be described with reference to FIGs. 4 through 16.
[0112] FIG. 4 shows an example of a wireless communications system 400 that supports dataset generation for encoder training in accordance with one or more aspects of the present disclosure. In some examples, the wireless communications system 400 may implement or be implemented by the wireless communications system 100. For example, the wireless communications system 400 may include a network entity 105-aand a network entity 105-b, which may represent examples of corresponding devices described herein with reference to FIG. 1. The network entity 105-a may communicate with the network entity 105-b via a communication link 125. The communication link 125 may be examples of an uplink communication link, a downlink communication link, a Uu link, a sidelink, a backhaul link, a D2D link, some other type of communication link 125 described herein with reference to FIG. 1, or any combination thereof.
[0113] In some examples of the wireless communications system 400, the network entity 105-a, the network entity 105-b, or both may have a CSI report configuration to transmit CSI feedback. In some cases, the CSI report configuration may include a codebook which is used as a PMI dictionary from which a network entity 105 can report PMI codewords and use a sequence of bits to report the PMI. In some cases, AI-based CSI feedback reporting may replace the use of a CSI codebook with a CSI encoder and decoder. For example, a CSI encoder 410 may be used to perform the functions of a PMI searching algorithm and a CSI encoder may be used to perform the functions of a PMI codebook which is used to translate the CSI reporting bits to a PMI codeword. In some examples, the input to an encoder may include a downlink channel matrix, downlink precoders, an inference covariance matrix, or any combination thereof. Further, the encoder, which may be at the network entity 105-b, may generate a first message 415 (e.g., a latent message) that includes the CSI data for the network entity 105-a to decode. To decode the CSI data, the network entity 105-a may have a decoder that generates an output that may include a downlink channel matrix, a transmission covariance matrix, downlink precoders, an inference covariance matrix, raw channel data, whitened downlink channel data, or any combination thereof.
[0114] In some examples, the network entity 105-a and the network entity 105-b may collaborate to train the CSI encoder 410 at the network entity 105-b and to train the CSI decoder 420 at the network entity 105-a. In some cases, the training may be a joint training at a single entity. For example, a training entity at the network entity 105-a or the network entity 105-b may train both the CSI encoder 410 for the network entity
[0115] 105-b and the CSI decoder 420 for the network entity 105-a. Further, in some cases, inter-vendor collaboration may occur outside of the training process. For example, a model structure and input format alignment may be determined before the training process. The inter-vendor collaboration may also include collaborating on a procedure for a model delivery and transfer between network entities 105 (e.g., the network entity 105-a transferring an AI / ML model for the CSI encoder 410 to the network entity
[0116] 105-b) , a procedure for model compilation and testing subsequent to a training process, or both. In some other cases, the training may be a joint training across the network entity 105-a and the network entity 105-b. In such case, there may be close inter-vendor collaboration during the training process (e.g., collaboration via application programming interfaces (APIs) to exchange activation and gradient information or data) . Further, in some examples, when training the CSI encoder 410 and the CSI decoder 420 across the network entity 105-a and the network entity 105-b the training may be simultaneous. For example, the CSI encoder 410 and the CSI decoder 420 may be trained or updated concurrently in a distributed manner. In some other examples, the training may be sequential where the CSI encoder 410 may be trained with a frozen CSI decoder 420, or vice versa. In another case, the training of the CSI encoder 410 and the CSI decoder 420 may be separated between the network entity 105-a and the network entity 105-b. For example, the network entity 105-a may train the CSI decoder 420 first and then share the model information with the network entity 105-a to use for training the CSI encoder 410. In such cases, the inter-vendor collaboration may be relatively light and may occur outside of the training process. For example, vendors may exchange dataset pairs (e.g., latent vectors, procedures, and the like) . Additionally, or alternatively, the datasets should also account for payload quantization. Moreover, in some cases, the separated training may also start at the network entity 105-b rather than the network entity 105-a.
[0117] In some examples, for inter-vendor collaboration, both the network entity 105-a and the network entity 105-b may develop models (e.g., AI / ML models) for the CSI decoder 420 and the CSI encoder 410 respectively to be compatible to a reference model. Further, the development of the models at the network entity 105-a and the network entity 105-b may be independent from each other without coordination. In some other examples, the network entity 105-a and the network entity 105-b may both use the same dataset for model training. In another example, the network entity 105-a, the network entity 105-b, or both may share or transfer models or model parameters. In some cases, the network entity 105-a may share the models or model parameters to a server associated with the network entity 105-b (e.g., a UE 115 side server) to facilitate offline engineering (e.g., potential re-training, re-development of a different model, offline testing, or any combination thereof) . For example, the network entity 105-a may transfer or share encoder parameters, decoder parameters, an entire encoder model, an entire decoder model, or any combination thereof. In some other cases, the network entity 105-a may transfer the model or model parameters for inference directly by the network entity 105-b. That is, the network entity 105-b may implement or use the model parameters or models that are obtained from the network entity 105-a directly for performing inferences without any additional training. Additionally, or alternatively, the network entity 105-a, the network entity 105-b, or both may share datasets to facilitate the offline engineering. For example, the network entity 105-a may share encoder inputs and outputs, decoder inputs and outputs, or both. The techniques of the present disclosure may be based on the network entity 105-a or the network entity 105-b sharing encoder inputs and outputs (e.g., target CSI data, latent message outputs by an encoder trained by the network entity 105-a) , the network entity 105-a or the network entity 105-b sharing encoder parameters and target CSI data (e.g., encoder inputs) , or both.
[0118] To perform the offline engineering at the network entity 105-b when the CSI encoder 410 and the CSI decoder 420 are trained separately, the network entity 105-amay share information with the network entity 105-b to assist the network entity 105-b in generating and training the CSI encoder 410. In some cases, prior to sharing such information, the network entity 105-a may train a CSI decoder 420 by generating a CSI encoder 425 using a set of input data 430 that is collected from various vendors (e.g., UE 115 vendors, chip vendors, and the like) . The network entity 105-a may then generate an encoder output 435 that is input into to the CSI decoder 420 to generate a decoder output 440. Further, as illustrated herein, the CSI encoder 425 at the network entity 105-a may a darker shade to represent that the CSI encoder 425 is a nominal CSI encoder at network entity 105-a. It may be different from the CSI encoder 410 at the network entity 105-b. In some cases, the CSI encoder 425 may thus be referred to as a nominal encoder, a predicted encoder, an estimated encoder, or any combination thereof.
[0119] Moreover, in some examples, to train the CSI encoder 410 at the network entity 105-b, the network entity 105-a may exchange encoder parameters to the network entity 105-b. In some cases, as shown via 401, to train the CSI encoder 410, the network entity 105-b may first develop a CSI decoder 445 (e.g., a CSI decoder 445-a) against an CSI encoder 450 (e.g., an CSI encoder 450-a) that is obtained from the network entity 105-a. For example, the network entity 105-a, may transmit a set of CSI data that is collected from a set of different vendors and the model or parameters of the CSI encoder 425 at the network entity 105-a. In this case, CSI encoder 450-a is the nominal CSI encoder trained at 105-a.. Then, once the CSI decoder 445-a is developed, the network entity 105-b may develop the CSI encoder 410 (e.g., a CSI encoder 410-a) against the CSI decoder 445-a. Further, the network entity 105-b may use a set of CSI data 453 at the network entity 105-b (e.g., UE 115 side data) that is specific to a vendor or chipset vendor associated with the network entity 105-b. In some other cases, as shown via 402, the network entity 105-b may directly develop and train the CSI encoder 410 (e.g., a CSI encoder 410-b) after receiving an CSI encoder 450 (e.g., an CSI encoder 450-b) that is obtained from the network entity 105-a (e.g., the CSI encoder 425) is generated. For example, the network entity 105-b develop the CSI encoder 410-b via the obtained encoder or encoder parameters (e.g., nominal CSI encoder 450-b, which is the nominal CSI encoder 425 developed by network entity 105-a) and the provided set of input data 430 from 105-a. Moreover, network entity 105-b may use the input data 430 and the obtained nominal CSI encoder 450-b to generate a CSI feedback 452. The network entity 105-b may then use the input data 430 and the generated CSI feedback 452 as the input and output of the encoder model to develop the actual encoder 410-b.
[0120] In some other examples, to train the CSI encoder 410 at the network entity 105-b, the network entity 105-a may share or exchange a set of CSI data (e.g., a dataset that includes target CSI data, CSI feedback data, and the like) to the network entity 105-b. In such examples, rather than sharing the CSI encoder 425 with the network entity 105-b, the network entity 105-a may transmit the set of input data 430 for the CSI encoder 425 and the encoder output 435 of the CSI encoder 425 at the network entity 105-a. Using such information, the network entity 105-b may then first train the CSI decoder 445 (e.g., a CSI decoder 445-b) that is a nominal decoder. In some cases, the training of the CSI decoder 445-b may include developing a decoder that when the encoder output 435 is given as an input, the set of input data 430 may be an expected output. Further, as shown via 403, the network entity 105-b may then develop the CSI encoder 410 (e.g., a CSI encoder 410-c) against the CSI decoder 445-b using the set of CSI data 453 at the network entity 105-b (e.g., UE 115 side data) that is specific to a vendor or chipset vendor associated with the network entity 105-b. Additionally, or alternatively, as shown via 402, the network entity 105-b may directly develop and train the CSI encoder 410 (e.g., the CSI encoder 410-b) . For example, the network entity 105-b may generate the CSI encoder 410-b by developing an encoder that when the set of input data 430 obtained from the network entity 105-a is given as an input, and the CSI feedback 452 as the expected output of the CSI encoder 410-c.
[0121] However, in some examples, sharing the set of input data 430 between the network entity 105-a and the network entity 105-b may result in security risks for vendors. For example, when the network entity 105-a trains the CSI decoder 420 (e.g., during network side training) , the network entity 105-a may collect data (e.g., the network entity 105-a may perform network side data collection) from various different vendors (e.g., UE 115 vendors, chipset vendors, or both) to train the CSI decoder 420 and the CSI encoder 425 using the collected dataset (e.g., an aggregation of all the UE 115 vendors or chipset vendors data) . Moreover, to facilitate the training at the network entity 105-b (e.g., UE 115 side training) , the network entity 105-a may share the dataset to the network entity 105-b that is associated with a respective vendor (e.g., UE 115 vendor or chipset vendor) . As such, a network entity 105 from a first vendor may be able to access data from a second vendor which can cause a security risk due to proprietary data and information of the second vendor being accessible by network entities 105 of the first vendor. To prevent the potential security risks, the techniques of the present disclosure may describe a set of CSI data being synthesized from the set of CSI data at the network entity 105-a such that the network entity 105-b can efficiently train the CSI encoder 410 at the network entity 105-b without using the set of CSI data at the network entity 105-a that includes data from various different vendors.
[0122] In some examples, in accordance with the techniques of the present disclosure, the network entity 105-a (e.g., a first network entity) may generate and share a first set of CSI data 455 that is based on a second set of CSI data at the network entity 105-a and is a synthesized version of the second set of CSI data. Further, the network entity 105-a may generate the first set of CSI data 455 such that the first set of CSI data 455 has a relatively similar distribution as the second set of CSI data (e.g., the actual set of CSI data) . Additionally, or alternatively, the first set of CSI data 455 may be referred to as a synthesized set of CSI data, a synthesized CSI dataset, an emulated dataset, or any combination thereof. Further, the network entity 105-a may generate the first set of CSI data 455 via synthetic methods using a synthetic channel model or by using random vectors or random matrices (e.g., the entries of a vector or matrix may be independent from each other and the vectors and matrices may be independent from each other) . Moreover, the first set of CSI data 455 (e.g., the synthesized dataset) may be generated to achieve a relatively similar performance as the second set of CSI data (e.g., the actual dataset) when running inference using an AI / ML model developed by the second set of CSI data.
[0123] In some cases, to generate the first set of CSI data 455, the network entity 105-a may first develop the CSI encoder 425 and the CSI decoder 420 using the second set of CSI data at the network entity 105-a that is collected from a data collection procedure. Further, the second set of CSI data (e.g., the actual dataset) may be denoted as dataset A and a model pair (e.g., the CSI encoder 425 and the CSI decoder 420 pair) may be denoted as E1_D1 such that a performance indication (e.g., a key performance indicator (KPI) that is a result of an inference using the model pair on the second set of CSI data may be a function of a difference between the second set of CSI data and an output of the CSI encoder 425 and the CSI decoder 420 at the network entity 105-a using the second set of CSI data (e.g., KPA_A=f (E1_D1 (dataset A) , dataset A) ) . In some cases, the function f (x, y) is the cosine similarity between vector x and y, e.g., where xH denotes the Hermitian of vector x, ‖x‖is the norm of vector x. Further, KPI may be defined as the cosine similarity between the input to the CSI encoder and the output of CSI decoder. Moreover, once the network entity 105-adevelops the CSI encoder 425 and the CSI decoder 420, the network entity 105-a may generate the first set of CSI data 455 where a performance indication of the first set of CSI data 455 should be relatively similar to the performance indication of the second set of CSI data. For example, the network entity 105-a may generate the first set of CSI data 455 (e.g., a dataset B) to be associated with a second performance indication (e.g., KPI_B) that is a function of a difference between the first set of CSI data 455 and an output of the CSI encoder 410 at the network entity 105-b and CSI decoder 445 at the network entity 105-b using the first set of CSI data 455 (e.g., KPA_B=f (E1_D1 (dataset B) , dataset B) ) .
[0124] In some cases, the first set of CSI data 455 may also be generated such that a quantity of CSI data samples satisfy one or more thresholds (e.g., KPI thresholds) . For example, the first set of CSI data 455 may include a first quantity of CSI data samples (e.g., N1 samples) that satisfy a first threshold (e.g., KPI_B>=thr1) and a second quantity of CSI data samples (e.g., N2 samples) that satisfy a second condition or threshold (e.g., KPI_B >= thr2 and <thr1) . Further, the values of the quantity of CSI data samples may be given by a quantity of samples in the second set of CSI data at the network entity 105-a that satisfy the one or more thresholds (e.g., data samples where KPI_A>= thr1, KPI_A>= thr2 and <thr1, etc) . In some other cases, the CSI data samples for the first set of CSI data 455 may be obtained from a third set of CSI data (e.g., a superset dataset S) . In such cases, the network entity 105-a may select a quantity of samples from the third set of CSI data such that the quantity of samples satisfy the one or more thresholds. Thus, once the network entity 105-a generates the first set of CSI data 455, the network entity 105-a may output the first set of CSI data 455 to the network entity 105-b for training the CSI encoder 410 at the network entity 105-b. The first set of CSI data may be generated using random vectors (e.g., entries are independent isotropic Gaussian) or using standardized channel modelling in standardization, or as linear combination or any pre-processing of the second CSI data. Moreover, the network entity 105-a may first generate a sufficient quantity of samples for the third CSI data (dataset S) using the random vectors or standardized channel modelling. Then according to the samples in dataset A that satisfies one or more conditions, the network entity 105-a may select the corresponding quantity of samples from the third CSI dataset step by step for the one or more conditions.
[0125] In some examples, rather than the network entity 105-a generating the first set of CSI data 455, the network entity 105-b may generate the first set of CSI data 455. To generate the first set of CSI data 455, the network entity 105-b may obtain, from the network entity 105-a, a set of parameters for the CSI encoder 425 at the network entity 105-a and a set of information associated with the encoder output 435 of the CSI encoder 425 (e.g., the network entity 105-b may obtain a set of CSI encoder parameters and output information 460 from the network entity 105-a) . Moreover, the encoder output 435 of the CSI encoder 425 is based on the second set of CSI data at the network entity 105-a (e.g., the actual set of CSI data collected via the network data collection) . That is, the network entity 105-b may receive an encode model or parameters from the network entity 105-a and information associated with the encoder output generated by the network entity 105-a using the set of CSI data from the various different vendors. In some examples, when the network entity 105-b obtains the set of information associated with the encoder output 435 of the CSI encoder 425 (e.g., E1) , via the set of CSI encoder parameters and output information 460, the network entity 105-b may explicitly obtain the encoder output 435 (e.g., z_A=E1 (dataset A) . In some other examples, the network entity 105-b may obtain a set of statistics associated with the encoder output 435. For example, the set of statistics associated with encoder output 435 may indicate a quantity of data samples that when used to generate the encoder output 435 are equal to one or more respective values (e.g., N1=# {z_A=z1} , N2=# {z_A=z2} , etc) . Moreover, the network entity 105-a may refrain from providing the set of information associated with the encoder output 435 if the majority of the inference results using the second set of CSI data satisfy one or more thresholds (e.g., z_A= {z_i, where KPI (z_i) >= threshold} ) .
[0126] Once the network entity 105-b obtains the set of CSI encoder parameters and output information 460, the network entity 105-b may then generate the first set of CSI data 455 such that the output of the CSI encoder 410 when using the first set of CSI data 455 is similar to as if the network entity 105-b used the second set of CSI data (e.g., z_B≈z_A, where z_B = E1 (dataset B) ) . Moreover, the network entity 105-b may generate the first set of CSI data 455 using a synthetic channel model, random vectors, random matrices, or any combination thereof as described herein. In some cases, the network entity 105-b may generate the first set of CSI data 455 such that the first set of CSI data 455 includes a quantity of CSI data samples that when used as input to the CSI encoder 410 are equal to one or more values of the encoder output 435 of the CSI encoder 425 of the network entity 105-a. Additionally, or alternatively, the network entity 105-b may select a quantity of CSI data samples for the first set of CSI data 455 from a third set of CSI data (e.g., a superset dataset S) . Further, the network entity 105-b may select the quantity of CSI data samples from the third set of CSI data such that when used as input to the CSI encoder 410 are equal to one or more values of the encoder output 435 of the CSI encoder 425 of the network entity 105-a. Moreover, it should be understood by one having ordinary skill in the art that the first set of CSI data 455 may also be referred to as a second set of CSI data and the second set of CSI data that is at the network entity 105-a may be referred to as a first set of CSI data.
[0127] Therefore, by having the network entity 105-a or the network entity 105-b generate the first set of CSI data 455 for the network entity 105-b to train the CSI encoder 410 (e.g., the CSI encoder 410-a, the CSI encoder 410-b, the CSI encoder 410-c) , the network entity 105-b may encode a CSI data to generate the first message 415 (e.g., a latent message) for the network entity 105-a. Moreover, the techniques of the present disclosure may ensure that the network entity 105-a refrains from sharing vendor-specific information and data with the network entity 105-b while enabling the network entity 105-b to accurately and efficiently train the CSI encoder 410 at the network entity 105-b. Further descriptions of the techniques of the present disclosure may be described elsewhere herein, such as with reference to FIGs. 5 and 6.
[0128] FIG. 5 shows an example of a process flow 500 that supports dataset generation for encoder training in accordance with one or more aspects of the present disclosure. In some examples, the process flow 500 may implement or may be implemented by the wireless communications system 100, the wireless communications system 400, or both. The process flow 500 may include a network entity 105-a and a network entity 105-b which may be examples of devices or services described elsewhere herein including with reference to FIG. 1.
[0129] In the following description of the process flow 500, the operations may be performed by the network entity 105-a and the network entity 105-b in different orders or at different times. Some operations may also be left out of the process flow 500, or other operations may be added. Although the process flow 500 may be described as being performed by the network entity 105-a and the network entity 105-b, some aspects of some operations may also be performed by other devices, services, or models described elsewhere herein including with reference to FIGs. 1 and 4.
[0130] At 505, the network entity 105-a (e.g., a first network entity 105) may generate, at the network entity 105-a, a first set of CSI data that is on a second set of CSI data at the network entity 105-a, the second set of CSI data being associated with a training of a first CSI decoder at the network entity 105-a, wherein the first set of CSI data being a synthesized version of the second set of CSI data. In some examples, the second set of CSI data may be associated with a first performance indication that is a function of a difference between the second set of CSI data and an output of a first CSI encoder at the network entity 105-a (e.g., a second CSI decoder at the first network entity) and the first CSI decoder at the network entity 105-a using the second set of CSI data. Further, the first set of CSI data may be associated with a second performance indication that is a function of a difference between the first set of CSI data and an output of the second CSI encoder at the network entity 105-a and the first CSI decoder at the network entity 105-a using the first set of CSI data. Moreover, generation of the first set of CSI data may be based on the second performance indication being associated with the first performance indication that is associated with the second set of CSI data based on the second performance indication satisfying one or more thresholds.
[0131] In some examples, the network entity 105-a may generate the first set of CSI data based on the first set of CSI data satisfying a set of thresholds. Further, the set of thresholds may be KPI thresholds. Moreover, in some cases, a first quantity of CSI data samples within the first set of CSI data that satisfy the set of thresholds may be based on the second set of CSI data including a second quantity of CSI data samples that satisfy the set of thresholds. Additionally, or alternatively, the first set of CSI data may include a quantity of CSI data samples from a third set of CSI data where the quantity of CSI data samples from the third set of CSI data may be based on the quantity of CSI data samples satisfying one or more respective threshold. Moreover, in some cases, the network entity 105-a may generate the first set of CSI data via a synthetic channel model, one or more random vectors, one or more random matrices, or any combination thereof.
[0132] At 510, the network entity 105-a may output, to the network entity 105-b, the first set of CSI data for training a first CSI encoder at the network entity 105-b. Then, at 515, the network entity 105-a may obtain, from the network entity 105-b, a first message based on outputting the first set of CSI data to the network entity 105-b. At 510, the set of CSI data includes the target CSI of the first set of CSI data and also the associated CSI encoder output using the target CSI of the first set of CSI data. At 510, the message may further comprise CSI encoder or CSI encoder parameter where the CSI parameter is the one developed by network entity 105-a.
[0133] FIG. 6 shows an example of a process flow 600 that supports dataset generation for encoder training in accordance with one or more aspects of the present disclosure. In some examples, the process flow 600 may implement or may be implemented by the wireless communications system 100, the wireless communications system 400, or both. The process flow 600 may include a network entity 105-a and a network entity 105-b which may be examples of devices or services described elsewhere herein including with reference to FIG. 1.
[0134] In the following description of the process flow 600, the operations may be performed by the network entity 105-a and the network entity 105-b in different orders or at different times. Some operations may also be left out of the process flow 600, or other operations may be added. Although the process flow 600 may be described as being performed by the network entity 105-a and the network entity 105-b, some aspects of some operations may also be performed by other devices, services, or models described elsewhere herein including with reference to FIGs. 1 and 4.
[0135] At 605, the network entity 105-b may obtain, from the network entity 105-a, a set of parameters for a first CSI encoder at the network entity 105-a and a set of information associated with an output of the first CSI encoder, the output of the first CSI encoder being based at least in part on a first set of CSI data at the network entity 105-a. In some cases, the network entity 105-b may also obtain, from the network entity 105-a for one or more data samples within the first set of CSI data, an indication of one or more outputs of the first CSI encoder using the first set of CSI data, an indication of statistical information associated with the one or more outputs of the first CSI encoder using the first set of CSI data, or a combination thereof. Moreover, the network entity 105-b may obtain the set of information associated with the output of the first CSI encoder based on the output of a first CSI decoder at the network entity 105-a using the first set of CSI data satisfying one or more thresholds. Further, the one or more thresholds may be KPI thresholds.
[0136] At 610, the network entity 105-b may generate, at the network entity 105-b and in response to reception of the set of parameters and the set of information, a second set of CSI data for training a second CSI encoder at the network entity 105-b, the second set of CSI data being based on the first set of CSI data and being a synthesized version of the first set of CSI data. In some cases, generation of the second set of CSI data may be based on the network entity 105-b generating a quantity of data samples that result in an output of the second CSI encoder being equal to the one or more outputs of the first CSI encoder using the first set of CSI data. In another case, the network entity 105-b may select a quantity of data samples for the second set of CSI data from a third set of CSI data based on the output of the second CSI encoder using the quantity of data samples from the third set of CSI data being equal to the one or more outputs of the first CSI encoder using the first set of CSI data. Moreover, the network entity 105-b may generate the second set of CSI data via a synthetic channel model, one or more random vectors, one or more random matrices, or any combination thereof. Thus, at 615, the network entity 105-b may train, at the network entity 105-b and in response to generation of the second set of CSI data, the second CSI encoder using the second set of CSI data. Further, at 620, the network entity 105-b may output, to the network entity 105-a, a first message that is obtained via the second CSI encoder based on training the second CSI encoder using the second set of CSI data.
[0137] FIG. 7 shows a block diagram 700 of a device 705 that supports dataset generation for encoder training in accordance with one or more aspects of the present disclosure. The device 705 may be an example of aspects of a network entity 105 as described herein. The device 705 may include a receiver 710, a transmitter 715, and a communications manager 720. The device 705, or one or more components of the device 705 (e.g., the receiver 710, the transmitter 715, the communications manager 720) , may include at least one processor, which may be coupled with at least one memory, to, individually or collectively, support or enable the described techniques. Each of these components may be in communication with one another (e.g., via one or more buses) .
[0138] The receiver 710 may provide a means for obtaining (e.g., receiving, determining, identifying) information such as user data, control information, or any combination thereof (e.g., I / Q samples, symbols, packets, protocol data units, service data units) associated with various channels (e.g., control channels, data channels, information channels, channels associated with a protocol stack) . Information may be passed on to other components of the device 705. In some examples, the receiver 710 may support obtaining information by receiving signals via one or more antennas. Additionally, or alternatively, the receiver 710 may support obtaining information by receiving signals via one or more wired (e.g., electrical, fiber optic) interfaces, wireless interfaces, or any combination thereof.
[0139] The transmitter 715 may provide a means for outputting (e.g., transmitting, providing, conveying, sending) information generated by other components of the device 705. For example, the transmitter 715 may output information such as user data, control information, or any combination thereof (e.g., I / Q samples, symbols, packets, protocol data units, service data units) associated with various channels (e.g., control channels, data channels, information channels, channels associated with a protocol stack) . In some examples, the transmitter 715 may support outputting information by transmitting signals via one or more antennas. Additionally, or alternatively, the transmitter 715 may support outputting information by transmitting signals via one or more wired (e.g., electrical, fiber optic) interfaces, wireless interfaces, or any combination thereof. In some examples, the transmitter 715 and the receiver 710 may be co-located in a transceiver, which may include or be coupled with a modem.
[0140] The communications manager 720, the receiver 710, the transmitter 715, or various combinations or components thereof may be examples of means for performing various aspects of dataset generation for encoder training as described herein. For example, the communications manager 720, the receiver 710, the transmitter 715, or various combinations or components thereof may be capable of performing one or more of the functions described herein.
[0141] In some examples, the communications manager 720, the receiver 710, the transmitter 715, or various combinations or components thereof may be implemented in hardware (e.g., in communications management circuitry) . The hardware may include at least one of a processor, a DSP, a CPU, an ASIC, an FPGA or other programmable logic device, a microcontroller, discrete gate or transistor logic, discrete hardware components, or any combination thereof configured as or otherwise supporting, individually or collectively, a means for performing the functions described in the present disclosure. In some examples, at least one processor and at least one memory coupled with the at least one processor may be configured to perform one or more of the functions described herein (e.g., by one or more processors, individually or collectively, executing instructions stored in the at least one memory) .
[0142] Additionally, or alternatively, the communications manager 720, the receiver 710, the transmitter 715, or various combinations or components thereof may be implemented in code (e.g., as communications management software or firmware) executed by at least one processor (e.g., referred to as a processor-executable code) . If implemented in code executed by at least one processor, the functions of the communications manager 720, the receiver 710, the transmitter 715, or various combinations or components thereof may be performed by a general-purpose processor, a DSP, a CPU, an ASIC, an FPGA, a microcontroller, or any combination of these or other programmable logic devices (e.g., configured as or otherwise supporting, individually or collectively, a means for performing the functions described in the present disclosure) .
[0143] In some examples, the communications manager 720 may be configured to perform various operations (e.g., receiving, obtaining, monitoring, outputting, transmitting) using or otherwise in cooperation with the receiver 710, the transmitter 715, or both. For example, the communications manager 720 may receive information from the receiver 710, send information to the transmitter 715, or be integrated in combination with the receiver 710, the transmitter 715, or both to obtain information, output information, or perform various other operations as described herein.
[0144] The communications manager 720 may support wireless communications in accordance with examples as disclosed herein. For example, the communications manager 720 is capable of, configured to, or operable to support a means for generating, at the first network entity, a first set of CSI data that is based on a second set of CSI data at the first network entity, the second set of CSI data being associated with a training of a first CSI decoder at the first network entity, where the first set of CSI data being a synthesized version of the second set of CSI data. The communications manager 720 is capable of, configured to, or operable to support a means for outputting, to a second network entity, the first set of CSI data for training a first CSI encoder at the second network entity. The communications manager 720 is capable of, configured to, or operable to support a means for obtaining, from the second network entity, a first message based on outputting the first set of CSI data to the second network entity.
[0145] By including or configuring the communications manager 720 in accordance with examples as described herein, the device 705 (e.g., at least one processor controlling or otherwise coupled with the receiver 710, the transmitter 715, the communications manager 720, or a combination thereof) may support techniques for generating a synthesized dataset to improve the security of a CSI encoder and CSI decoder that can be utilized to support reduced processing, reduced power consumption, and more efficient utilization of communication resources.
[0146] FIG. 8 shows a block diagram 800 of a device 805 that supports dataset generation for encoder training in accordance with one or more aspects of the present disclosure. The device 805 may be an example of aspects of a device 705 or a network entity 105 as described herein. The device 805 may include a receiver 810, a transmitter 815, and a communications manager 820. The device 805, or one or more components of the device 805 (e.g., the receiver 810, the transmitter 815, the communications manager 820) , may include at least one processor, which may be coupled with at least one memory, to support the described techniques. Each of these components may be in communication with one another (e.g., via one or more buses) .
[0147] The receiver 810 may provide a means for obtaining (e.g., receiving, determining, identifying) information such as user data, control information, or any combination thereof (e.g., I / Q samples, symbols, packets, protocol data units, service data units) associated with various channels (e.g., control channels, data channels, information channels, channels associated with a protocol stack) . Information may be passed on to other components of the device 805. In some examples, the receiver 810 may support obtaining information by receiving signals via one or more antennas. Additionally, or alternatively, the receiver 810 may support obtaining information by receiving signals via one or more wired (e.g., electrical, fiber optic) interfaces, wireless interfaces, or any combination thereof.
[0148] The transmitter 815 may provide a means for outputting (e.g., transmitting, providing, conveying, sending) information generated by other components of the device 805. For example, the transmitter 815 may output information such as user data, control information, or any combination thereof (e.g., I / Q samples, symbols, packets, protocol data units, service data units) associated with various channels (e.g., control channels, data channels, information channels, channels associated with a protocol stack) . In some examples, the transmitter 815 may support outputting information by transmitting signals via one or more antennas. Additionally, or alternatively, the transmitter 815 may support outputting information by transmitting signals via one or more wired (e.g., electrical, fiber optic) interfaces, wireless interfaces, or any combination thereof. In some examples, the transmitter 815 and the receiver 810 may be co-located in a transceiver, which may include or be coupled with a modem.
[0149] The device 805, or various components thereof, may be an example of means for performing various aspects of dataset generation for encoder training as described herein. For example, the communications manager 820 may include a CSI dataset generation component 825, a CSI dataset output component 830, a first message acquisition component 835, or any combination thereof. The communications manager 820 may be an example of aspects of a communications manager 720 as described herein. In some examples, the communications manager 820, or various components thereof, may be configured to perform various operations (e.g., receiving, obtaining, monitoring, outputting, transmitting) using or otherwise in cooperation with the receiver 810, the transmitter 815, or both. For example, the communications manager 820 may receive information from the receiver 810, send information to the transmitter 815, or be integrated in combination with the receiver 810, the transmitter 815, or both to obtain information, output information, or perform various other operations as described herein.
[0150] The communications manager 820 may support wireless communications in accordance with examples as disclosed herein. The CSI dataset generation component 825 is capable of, configured to, or operable to support a means for generating, at the first network entity, a first set of CSI data that is based on a second set of CSI data at the first network entity, the second set of CSI data being associated with a training of a first CSI decoder at the first network entity, where the first set of CSI data being a synthesized version of the second set of CSI data. The CSI dataset output component 830 is capable of, configured to, or operable to support a means for outputting, to a second network entity, the first set of CSI data for training a first CSI encoder at the second network entity. The first message acquisition component 835 is capable of, configured to, or operable to support a means for obtaining, from the second network entity, a first message based on outputting the first set of CSI data to the second network entity.
[0151] FIG. 9 shows a block diagram 900 of a communications manager 920 that supports dataset generation for encoder training in accordance with one or more aspects of the present disclosure. The communications manager 920 may be an example of aspects of a communications manager 720, a communications manager 820, or both, as described herein. The communications manager 920, or various components thereof, may be an example of means for performing various aspects of dataset generation for encoder training as described herein. For example, the communications manager 920 may include a CSI dataset generation component 925, a CSI dataset output component 930, a first message acquisition component 935, or any combination thereof. Each of these components, or components or subcomponents thereof (e.g., one or more processors, one or more memories) , may communicate, directly or indirectly, with one another (e.g., via one or more buses) .
[0152] The communications manager 920 may support wireless communications in accordance with examples as disclosed herein. The CSI dataset generation component 925 is capable of, configured to, or operable to support a means for generating, at the first network entity, a first set of CSI data that is based on a second set of CSI data at the first network entity, the second set of CSI data being associated with a training of a first CSI decoder at the first network entity, where the first set of CSI data being a synthesized version of the second set of CSI data. The CSI dataset output component 930 is capable of, configured to, or operable to support a means for outputting, to a second network entity, the first set of CSI data for training a first CSI encoder at the second network entity. The first message acquisition component 935 is capable of, configured to, or operable to support a means for obtaining, from the second network entity, a first message based on outputting the first set of CSI data to the second network entity.
[0153] In some examples, the second set of CSI data is associated with a first performance indication that is a function of a difference between the second set of CSI data and an output of a second CSI encoder at the first network entity and the first CSI decoder at the first network entity using the second set of CSI data.
[0154] In some examples, the first set of CSI data is associated with a second performance indication that is a function of a difference between the first set of CSI data and an output of the second CSI encoder at the first network entity and the first CSI decoder at the first network entity using the first set of CSI data and generation of the first set of CSI data is based at least in part on the second performance indication satisfying one or more thresholds.
[0155] In some examples, to support generating the first set of CSI data, the CSI dataset generation component 925 is capable of, configured to, or operable to support a means for generating, at the first network entity, the first set of CSI data based on the first set of CSI data satisfying a set of thresholds.
[0156] In some examples, the set of thresholds are key performance indicator thresholds.
[0157] In some examples, a first quantity of CSI data samples within the first set of CSI data that satisfy the set of thresholds is based on the second set of CSI data including a second quantity of CSI data samples that satisfy the set of thresholds.
[0158] In some examples, the first set of CSI data includes a quantity of CSI data samples from a third set of CSI data.
[0159] In some examples, the first set of CSI data includes the quantity of CSI data samples from the third set of CSI data based on the quantity of CSI data samples satisfying one or more respective threshold.
[0160] In some examples, the first set of CSI data is generated via a synthetic channel model, one or more random vectors, one or more random matrices, or any combination thereof.
[0161] FIG. 10 shows a diagram of a system 1000 including a device 1005 that supports dataset generation for encoder training in accordance with one or more aspects of the present disclosure. The device 1005 may be an example of or include components of a device 705, a device 805, or a network entity 105 as described herein. The device 1005 may include components for bi-directional voice and data communications including components for transmitting and receiving communications, such as a communications manager 1020, a transceiver 1010, one or more antennas 1015, at least one memory 1025, code 1030, and at least one processor 1035. These components may be in electronic communication or otherwise coupled (e.g., operatively, communicatively, functionally, electronically, electrically) via one or more buses (e.g., a bus 1040) .
[0162] The transceiver 1010 may support bi-directional communications via wired links, wireless links, or both as described herein. In some examples, the transceiver 1010 may include a wired transceiver and may communicate bi-directionally with another wired transceiver. Additionally, or alternatively, in some examples, the transceiver 1010 may include a wireless transceiver and may communicate bi-directionally with another wireless transceiver. In some examples, the device 1005 may include one or more antennas 1015, which may be capable of transmitting or receiving wireless transmissions (e.g., concurrently) . The transceiver 1010 may also include a modem to modulate signals, to provide the modulated signals for transmission (e.g., by one or more antennas 1015, by a wired transmitter) , to receive modulated signals (e.g., from one or more antennas 1015, from a wired receiver) , and to demodulate signals. In some implementations, the transceiver 1010 may include one or more interfaces, such as one or more interfaces coupled with the one or more antennas 1015 that are configured to support various receiving or obtaining operations, or one or more interfaces coupled with the one or more antennas 1015 that are configured to support various transmitting or outputting operations, or a combination thereof. In some implementations, the transceiver 1010 may include or be configured for coupling with one or more processors or one or more memory components that are operable to perform or support operations based on received or obtained information or signals, or to generate information or other signals for transmission or other outputting, or any combination thereof. In some implementations, the transceiver 1010, or the transceiver 1010 and the one or more antennas 1015, or the transceiver 1010 and the one or more antennas 1015 and one or more processors or one or more memory components (e.g., the at least one processor 1035, the at least one memory 1025, or both) , may be included in a chip or chip assembly that is installed in the device 1005. In some examples, the transceiver 1010 may be operable to support communications via one or more communications links (e.g., communication link (s) 125, backhaul communication link (s) 120, a midhaul communication link 162, a fronthaul communication link 168) .
[0163] The at least one memory 1025 may include RAM, ROM, or any combination thereof. The at least one memory 1025 may store computer-readable, computer-executable, or processor-executable code, such as the code 1030. The code 1030 may include instructions that, when executed by one or more of the at least one processor 1035, cause the device 1005 to perform various functions described herein. The code 1030 may be stored in a non-transitory computer-readable medium such as system memory or another type of memory. In some cases, the code 1030 may not be directly executable by a processor of the at least one processor 1035 but may cause a computer (e.g., when compiled and executed) to perform functions described herein. In some cases, the at least one memory 1025 may include, among other things, a BIOS which may control basic hardware or software operation such as the interaction with peripheral components or devices. In some examples, the at least one processor 1035 may include multiple processors and the at least one memory 1025 may include multiple memories. One or more of the multiple processors may be coupled with one or more of the multiple memories which may, individually or collectively, be configured to perform various functions herein (for example, as part of a processing system) .
[0164] The at least one processor 1035 may include one or more intelligent hardware devices (e.g., one or more general-purpose processors, one or more DSPs, one or more CPUs, one or more graphics processing units (GPUs) , one or more neural processing units (NPUs) (also referred to as neural network processors or deep learning processors (DLPs) ) , one or more microcontrollers, one or more ASICs, one or more FPGAs, one or more programmable logic devices, discrete gate or transistor logic, one or more discrete hardware components, or any combination thereof) . In some cases, the at least one processor 1035 may be configured to operate a memory array using a memory controller. In some other cases, a memory controller may be integrated into one or more of the at least one processor 1035. The at least one processor 1035 may be configured to execute computer-readable instructions stored in a memory (e.g., one or more of the at least one memory 1025) to cause the device 1005 to perform various functions (e.g., functions or tasks supporting dataset generation for encoder training) . For example, the device 1005 or a component of the device 1005 may include at least one processor 1035 and at least one memory 1025 coupled with one or more of the at least one processor 1035, the at least one processor 1035 and the at least one memory 1025 configured to perform various functions described herein. The at least one processor 1035 may be an example of a cloud-computing platform (e.g., one or more physical nodes and supporting software such as operating systems, virtual machines, or container instances) that may host the functions (e.g., by executing code 1030) to perform the functions of the device 1005. The at least one processor 1035 may be any one or more suitable processors capable of executing scripts or instructions of one or more software programs stored in the device 1005 (such as within one or more of the at least one memory 1025) .
[0165] In some examples, the at least one processor 1035 may include multiple processors and the at least one memory 1025 may include multiple memories. One or more of the multiple processors may be coupled with one or more of the multiple memories, which may, individually or collectively, be configured to perform various functions herein. In some examples, the at least one processor 1035 may be a component of a processing system, which may refer to a system (such as a series) of machines, circuitry (including, for example, one or both of processor circuitry (which may include the at least one processor 1035) and memory circuitry (which may include the at least one memory 1025) ) , or components, that receives or obtains inputs and processes the inputs to produce, generate, or obtain a set of outputs. The processing system may be configured to perform one or more of the functions described herein. For example, the at least one processor 1035 or a processing system including the at least one processor 1035 may be configured to, configurable to, or operable to cause the device 1005 to perform one or more of the functions described herein. Further, as described herein, being “configured to, ” being “configurable to, ” and being “operable to” may be used interchangeably and may be associated with a capability, when executing code stored in the at least one memory 1025 or otherwise, to perform one or more of the functions described herein.
[0166] In some examples, a bus 1040 may support communications of (e.g., within) a protocol layer of a protocol stack. In some examples, a bus 1040 may support communications associated with a logical channel of a protocol stack (e.g., between protocol layers of a protocol stack) , which may include communications performed within a component of the device 1005, or between different components of the device 1005 that may be co-located or located in different locations (e.g., where the device 1005 may refer to a system in which one or more of the communications manager 1020, the transceiver 1010, the at least one memory 1025, the code 1030, and the at least one processor 1035 may be located in one of the different components or divided between different components) .
[0167] In some examples, the communications manager 1020 may manage aspects of communications with a core network 130 (e.g., via one or more wired or wireless backhaul links) . For example, the communications manager 1020 may manage the transfer of data communications for client devices, such as one or more UEs 115. In some examples, the communications manager 1020 may manage communications with one or more other network entities 105, and may include a controller or scheduler for controlling communications with UEs 115 (e.g., in cooperation with the one or more other network devices) . In some examples, the communications manager 1020 may support an X2 interface within an LTE / LTE-A wireless communications network technology to provide communication between network entities 105.
[0168] The communications manager 1020 may support wireless communications in accordance with examples as disclosed herein. For example, the communications manager 1020 is capable of, configured to, or operable to support a means for generating, at the first network entity, a first set of CSI data that is based on a second set of CSI data at the first network entity, the second set of CSI data being associated with a training of a first CSI decoder at the first network entity, where the first set of CSI data being a synthesized version of the second set of CSI data. The communications manager 1020 is capable of, configured to, or operable to support a means for outputting, to a second network entity, the first set of CSI data for training a first CSI encoder at the second network entity. The communications manager 1020 is capable of, configured to, or operable to support a means for obtaining, from the second network entity, a first message based on outputting the first set of CSI data to the second network entity.
[0169] By including or configuring the communications manager 1020 in accordance with examples as described herein, the device 1005 may support techniques for generating a synthesized dataset to improve the security of a CSI encoder and CSI decoder that can be utilized to support improved communication reliability, reduced latency, improved user experience related to reduced processing, reduced power consumption, more efficient utilization of communication resources, improved coordination between devices, longer battery life, and improved utilization of processing capability.
[0170] In some examples, the communications manager 1020 may be configured to perform various operations (e.g., receiving, obtaining, monitoring, outputting, transmitting) using or otherwise in cooperation with the transceiver 1010, the one or more antennas 1015 (e.g., where applicable) , or any combination thereof. Although the communications manager 1020 is illustrated as a separate component, in some examples, one or more functions described with reference to the communications manager 1020 may be supported by or performed by the transceiver 1010, one or more of the at least one processor 1035, one or more of the at least one memory 1025, the code 1030, or any combination thereof (for example, by a processing system including at least a portion of the at least one processor 1035, the at least one memory 1025, the code 1030, or any combination thereof) . For example, the code 1030 may include instructions executable by one or more of the at least one processor 1035 to cause the device 1005 to perform various aspects of dataset generation for encoder training as described herein, or the at least one processor 1035 and the at least one memory 1025 may be otherwise configured to, individually or collectively, perform or support such operations.
[0171] FIG. 11 shows a block diagram 1100 of a device 1105 that supports dataset generation for encoder training in accordance with one or more aspects of the present disclosure. The device 1105 may be an example of aspects of a network entity 105 as described herein. The device 1105 may include a receiver 1110, a transmitter 1115, and a communications manager 1120. The device 1105, or one or more components of the device 1105 (e.g., the receiver 1110, the transmitter 1115, the communications manager 1120) , may include at least one processor, which may be coupled with at least one memory, to, individually or collectively, support or enable the described techniques. Each of these components may be in communication with one another (e.g., via one or more buses) .
[0172] The receiver 1110 may provide a means for receiving information such as packets, user data, control information, or any combination thereof associated with various information channels (e.g., control channels, data channels, information channels related to dataset generation for encoder training) . Information may be passed on to other components of the device 1105. The receiver 1110 may utilize a single antenna or a set of multiple antennas.
[0173] The transmitter 1115 may provide a means for transmitting signals generated by other components of the device 1105. For example, the transmitter 1115 may transmit information such as packets, user data, control information, or any combination thereof associated with various information channels (e.g., control channels, data channels, information channels related to dataset generation for encoder training) . In some examples, the transmitter 1115 may be co-located with a receiver 1110 in a transceiver module. The transmitter 1115 may utilize a single antenna or a set of multiple antennas.
[0174] The communications manager 1120, the receiver 1110, the transmitter 1115, or various combinations or components thereof may be examples of means for performing various aspects of dataset generation for encoder training as described herein. For example, the communications manager 1120, the receiver 1110, the transmitter 1115, or various combinations or components thereof may be capable of performing one or more of the functions described herein.
[0175] In some examples, the communications manager 1120, the receiver 1110, the transmitter 1115, or various combinations or components thereof may be implemented in hardware (e.g., in communications management circuitry) . The hardware may include at least one of a processor, a DSP, a CPU, an ASIC, an FPGA or other programmable logic device, a microcontroller, discrete gate or transistor logic, discrete hardware components, or any combination thereof configured as or otherwise supporting, individually or collectively, a means for performing the functions described in the present disclosure. In some examples, at least one processor and at least one memory coupled with the at least one processor may be configured to perform one or more of the functions described herein (e.g., by one or more processors, individually or collectively, executing instructions stored in the at least one memory) .
[0176] Additionally, or alternatively, the communications manager 1120, the receiver 1110, the transmitter 1115, or various combinations or components thereof may be implemented in code (e.g., as communications management software or firmware) executed by at least one processor (e.g., referred to as a processor-executable code) . If implemented in code executed by at least one processor, the functions of the communications manager 1120, the receiver 1110, the transmitter 1115, or various combinations or components thereof may be performed by a general-purpose processor, a DSP, a CPU, an ASIC, an FPGA, a microcontroller, or any combination of these or other programmable logic devices (e.g., configured as or otherwise supporting, individually or collectively, a means for performing the functions described in the present disclosure) .
[0177] In some examples, the communications manager 1120 may be configured to perform various operations (e.g., receiving, obtaining, monitoring, outputting, transmitting) using or otherwise in cooperation with the receiver 1110, the transmitter 1115, or both. For example, the communications manager 1120 may receive information from the receiver 1110, send information to the transmitter 1115, or be integrated in combination with the receiver 1110, the transmitter 1115, or both to obtain information, output information, or perform various other operations as described herein.
[0178] The communications manager 1120 may support wireless communications in accordance with examples as disclosed herein. For example, the communications manager 1120 is capable of, configured to, or operable to support a means for obtaining, from a first network entity, a set of parameters for a first CSI encoder at the first network entity and a set of information associated with an output of the first CSI encoder, the output of the first CSI encoder being based on a first set of CSI data at the first network entity. The communications manager 1120 is capable of, configured to, or operable to support a means for generating, at the second network entity and in response to reception of the set of parameters and the set of information, a second set of CSI data for training a second CSI encoder at the second network entity, the second set of CSI data being based on the first set of CSI data and being a synthesized version of the first set of CSI data. The communications manager 1120 is capable of, configured to, or operable to support a means for training, at the second network entity and in response to generation of the second set of CSI data, the second CSI encoder using the second set of CSI data. The communications manager 1120 is capable of, configured to, or operable to support a means for outputting, to the first network entity, a first message that is obtained via the second CSI encoder based on training the second CSI encoder using the second set of CSI data.
[0179] By including or configuring the communications manager 1120 in accordance with examples as described herein, the device 1105 (e.g., at least one processor controlling or otherwise coupled with the receiver 1110, the transmitter 1115, the communications manager 1120, or a combination thereof) may support techniques for generating a synthesized dataset to improve the security of a CSI encoder and CSI decoder that can be utilized to support reduced processing, reduced power consumption, and more efficient utilization of communication resources.
[0180] FIG. 12 shows a block diagram 1200 of a device 1205 that supports dataset generation for encoder training in accordance with one or more aspects of the present disclosure. The device 1205 may be an example of aspects of a device 1105 or a network entity 105 as described herein. The device 1205 may include a receiver 1210, a transmitter 1215, and a communications manager 1220. The device 1205, or one or more components of the device 1205 (e.g., the receiver 1210, the transmitter 1215, the communications manager 1220) , may include at least one processor, which may be coupled with at least one memory, to support the described techniques. Each of these components may be in communication with one another (e.g., via one or more buses) .
[0181] The receiver 1210 may provide a means for receiving information such as packets, user data, control information, or any combination thereof associated with various information channels (e.g., control channels, data channels, information channels related to dataset generation for encoder training) . Information may be passed on to other components of the device 1205. The receiver 1210 may utilize a single antenna or a set of multiple antennas.
[0182] The transmitter 1215 may provide a means for transmitting signals generated by other components of the device 1205. For example, the transmitter 1215 may transmit information such as packets, user data, control information, or any combination thereof associated with various information channels (e.g., control channels, data channels, information channels related to dataset generation for encoder training) . In some examples, the transmitter 1215 may be co-located with a receiver 1210 in a transceiver module. The transmitter 1215 may utilize a single antenna or a set of multiple antennas.
[0183] The device 1205, or various components thereof, may be an example of means for performing various aspects of dataset generation for encoder training as described herein. For example, the communications manager 1220 may include a CSI encoder parameter and information acquisition component 1225, a CSI dataset generation component 1230, a CSI encoder training component 1235, a first message transmission component 1240, or any combination thereof. The communications manager 1220 may be an example of aspects of a communications manager 1120 as described herein. In some examples, the communications manager 1220, or various components thereof, may be configured to perform various operations (e.g., receiving, obtaining, monitoring, outputting, transmitting) using or otherwise in cooperation with the receiver 1210, the transmitter 1215, or both. For example, the communications manager 1220 may receive information from the receiver 1210, send information to the transmitter 1215, or be integrated in combination with the receiver 1210, the transmitter 1215, or both to obtain information, output information, or perform various other operations as described herein.
[0184] The communications manager 1220 may support wireless communications in accordance with examples as disclosed herein. The CSI encoder parameter and information acquisition component 1225 is capable of, configured to, or operable to support a means for obtaining, from a first network entity, a set of parameters for a first CSI encoder at the first network entity and a set of information associated with an output of the first CSI encoder, the output of the first CSI encoder being based on a first set of CSI data at the first network entity. The CSI dataset generation component 1230 is capable of, configured to, or operable to support a means for generating, at the second network entity and in response to reception of the set of parameters and the set of information, a second set of CSI data for training a second CSI encoder at the second network entity, the second set of CSI data being based on the first set of CSI data and being a synthesized version of the first set of CSI data. The CSI encoder training component 1235 is capable of, configured to, or operable to support a means for training, at the second network entity and in response to generation of the second set of CSI data, the second CSI encoder using the second set of CSI data. The first message transmission component 1240 is capable of, configured to, or operable to support a means for outputting, to the first network entity, a first message that is obtained via the second CSI encoder based on training the second CSI encoder using the second set of CSI data.
[0185] FIG. 13 shows a block diagram 1300 of a communications manager 1320 that supports dataset generation for encoder training in accordance with one or more aspects of the present disclosure. The communications manager 1320 may be an example of aspects of a communications manager 1120, a communications manager 1220, or both, as described herein. The communications manager 1320, or various components thereof, may be an example of means for performing various aspects of dataset generation for encoder training as described herein. For example, the communications manager 1320 may include a CSI encoder parameter and information acquisition component 1325, a CSI dataset generation component 1330, a CSI encoder training component 1335, a first message transmission component 1340, or any combination thereof. Each of these components, or components or subcomponents thereof (e.g., one or more processors, one or more memories) , may communicate, directly or indirectly, with one another (e.g., via one or more buses) .
[0186] The communications manager 1320 may support wireless communications in accordance with examples as disclosed herein. The CSI encoder parameter and information acquisition component 1325 is capable of, configured to, or operable to support a means for obtaining, from a first network entity, a set of parameters for a first CSI encoder at the first network entity and a set of information associated with an output of the first CSI encoder, the output of the first CSI encoder being based on a first set of CSI data at the first network entity. The CSI dataset generation component 1330 is capable of, configured to, or operable to support a means for generating, at the second network entity and in response to reception of the set of parameters and the set of information, a second set of CSI data for training a second CSI encoder at the second network entity, the second set of CSI data being based on the first set of CSI data and being a synthesized version of the first set of CSI data. The CSI encoder training component 1335 is capable of, configured to, or operable to support a means for training, at the second network entity and in response to generation of the second set of CSI data, the second CSI encoder using the second set of CSI data. The first message transmission component 1340 is capable of, configured to, or operable to support a means for outputting, to the first network entity, a first message that is obtained via the second CSI encoder based on training the second CSI encoder using the second set of CSI data.
[0187] In some examples, to support obtaining the set of information associated with the output of the first CSI encoder, the CSI encoder parameter and information acquisition component 1325 is capable of, configured to, or operable to support a means for obtaining, from the first network entity for one or more data samples within the first set of CSI data, an indication of one or more outputs of the first CSI encoder using the first set of CSI data, an indication of statistical information associated with the one or more outputs of the first CSI encoder using the first set of CSI data, or a combination thereof.
[0188] In some examples, to support generating the second set of CSI data, the CSI dataset generation component 1330 is capable of, configured to, or operable to support a means for generating a quantity of data samples that result in an output of the second CSI encoder being equal to the one or more outputs of the first CSI encoder using the first set of CSI data.
[0189] In some examples, to support generating the second set of CSI data, the CSI dataset generation component 1330 is capable of, configured to, or operable to support a means for selecting a quantity of data samples for the second set of CSI data from a third set of CSI data based on the output of the second CSI encoder using the quantity of data samples from the third set of CSI data being equal to the one or more outputs of the first CSI encoder using the first set of CSI data.
[0190] In some examples, the set of information associated with the output of the first CSI encoder is obtained based on the output of a first CSI decoder at the first network entity using the first set of CSI data satisfying one or more thresholds.
[0191] In some examples, the one or more thresholds are key performance indicator thresholds.
[0192] In some examples, the second set of CSI data is generated via a synthetic channel model, one or more random vectors, one or more random matrices, or any combination thereof.
[0193] FIG. 14 shows a diagram of a system 1400 including a device 1405 that supports dataset generation for encoder training in accordance with one or more aspects of the present disclosure. The device 1405 may be an example of or include components of a device 1105, a device 1205, or a network entity 105 as described herein. The device 1405 may include components for bi-directional voice and data communications including components for transmitting and receiving communications, such as a communications manager 1420, an I / O controller, such as an I / O controller 1410, a transceiver 1415, one or more antennas 1425, at least one memory 1430, code 1435, and at least one processor 1440. These components may be in electronic communication or otherwise coupled (e.g., operatively, communicatively, functionally, electronically, electrically) via one or more buses (e.g., a bus 1445) .
[0194] The I / O controller 1410 may manage input and output signals for the device 1405. The I / O controller 1410 may also manage peripherals not integrated into the device 1405. In some cases, the I / O controller 1410 may represent a physical connection or port to an external peripheral. In some cases, the I / O controller 1410 may utilize an operating system such as or another known operating system. Additionally, or alternatively, the I / O controller 1410 may represent or interact with a modem, a keyboard, a mouse, a touchscreen, or a similar device. In some cases, the I / O controller 1410 may be implemented as part of one or more processors, such as the at least one processor 1440. In some cases, a user may interact with the device 1405 via the I / O controller 1410 or via hardware components controlled by the I / O controller 1410.
[0195] In some cases, the device 1405 may include a single antenna. However, in some other cases, the device 1405 may have more than one antenna, which may be capable of concurrently transmitting or receiving multiple wireless transmissions. The transceiver 1415 may communicate bi-directionally via the one or more antennas 1425 using wired or wireless links as described herein. For example, the transceiver 1415 may represent a wireless transceiver and may communicate bi-directionally with another wireless transceiver. The transceiver 1415 may also include a modem to modulate the packets, to provide the modulated packets to one or more antennas 1425 for transmission, and to demodulate packets received from the one or more antennas 1425. The transceiver 1415, or the transceiver 1415 and one or more antennas 1425, may be an example of a transmitter 1115, a transmitter 1215, a receiver 1110, a receiver 1210, or any combination thereof or component thereof, as described herein.
[0196] The at least one memory 1430 may include RAM and ROM. The at least one memory 1430 may store computer-readable, computer-executable, or processor-executable code, such as the code 1435. The code 1435 may include instructions that, when executed by the at least one processor 1440, cause the device 1405 to perform various functions described herein. The code 1435 may be stored in a non-transitory computer-readable medium such as system memory or another type of memory. In some cases, the code 1435 may not be directly executable by the at least one processor 1440 but may cause a computer (e.g., when compiled and executed) to perform functions described herein. In some cases, the at least one memory 1430 may include, among other things, a BIOS which may control basic hardware or software operation such as the interaction with peripheral components or devices.
[0197] The at least one processor 1440 may include one or more intelligent hardware devices (e.g., one or more general-purpose processors, one or more DSPs, one or more CPUs, one or more graphics processing units (GPUs) , one or more neural processing units (NPUs) (also referred to as neural network processors or deep learning processors (DLPs) ) , one or more microcontrollers, one or more ASICs, one or more FPGAs, one or more programmable logic devices, discrete gate or transistor logic, one or more discrete hardware components, or any combination thereof) . In some cases, the at least one processor 1440 may be configured to operate a memory array using a memory controller. In some other cases, a memory controller may be integrated into the at least one processor 1440. The at least one processor 1440 may be configured to execute computer-readable instructions stored in a memory (e.g., the at least one memory 1430) to cause the device 1405 to perform various functions (e.g., functions or tasks supporting dataset generation for encoder training) . For example, the device 1405 or a component of the device 1405 may include at least one processor 1440 and at least one memory 1430 coupled with or to the at least one processor 1440, the at least one processor 1440 and the at least one memory 1430 configured to perform various functions described herein.
[0198] In some examples, the at least one processor 1440 may include multiple processors and the at least one memory 1430 may include multiple memories. One or more of the multiple processors may be coupled with one or more of the multiple memories, which may, individually or collectively, be configured to perform various functions described herein. In some examples, the at least one processor 1440 may be a component of a processing system, which may refer to a system (such as a series) of machines, circuitry (including, for example, one or both of processor circuitry (which may include the at least one processor 1440) and memory circuitry (which may include the at least one memory 1430) ) , or components, that receives or obtains inputs and processes the inputs to produce, generate, or obtain a set of outputs. The processing system may be configured to perform one or more of the functions described herein. For example, the at least one processor 1440 or a processing system including the at least one processor 1440 may be configured to, configurable to, or operable to cause the device 1405 to perform one or more of the functions described herein. Further, as described herein, being “configured to, ” being “configurable to, ” and being “operable to” may be used interchangeably and may be associated with a capability, when executing code 1435 (e.g., processor-executable code) stored in the at least one memory 1430 or otherwise, to perform one or more of the functions described herein.
[0199] The communications manager 1420 may support wireless communications in accordance with examples as disclosed herein. For example, the communications manager 1420 is capable of, configured to, or operable to support a means for obtaining, from a first network entity, a set of parameters for a first CSI encoder at the first network entity and a set of information associated with an output of the first CSI encoder, the output of the first CSI encoder being based on a first set of CSI data at the first network entity. The communications manager 1420 is capable of, configured to, or operable to support a means for generating, at the second network entity and in response to reception of the set of parameters and the set of information, a second set of CSI data for training a second CSI encoder at the second network entity, the second set of CSI data being based on the first set of CSI data and being a synthesized version of the first set of CSI data. The communications manager 1420 is capable of, configured to, or operable to support a means for training, at the second network entity and in response to generation of the second set of CSI data, the second CSI encoder using the second set of CSI data. The communications manager 1420 is capable of, configured to, or operable to support a means for outputting, to the first network entity, a first message that is obtained via the second CSI encoder based on training the second CSI encoder using the second set of CSI data.
[0200] By including or configuring the communications manager 1420 in accordance with examples as described herein, the device 1405 may support techniques for generating a synthesized dataset to improve the security of a CSI encoder and CSI decoder that can be utilized to support improved communication reliability, reduced latency, improved user experience related to reduced processing, reduced power consumption, more efficient utilization of communication resources, improved coordination between devices, longer battery life, and improved utilization of processing capability.
[0201] In some examples, the communications manager 1420 may be configured to perform various operations (e.g., receiving, monitoring, transmitting) using or otherwise in cooperation with the transceiver 1415, the one or more antennas 1425, or any combination thereof. Although the communications manager 1420 is illustrated as a separate component, in some examples, one or more functions described with reference to the communications manager 1420 may be supported by or performed by the at least one processor 1440, the at least one memory 1430, the code 1435, or any combination thereof. For example, the code 1435 may include instructions executable by the at least one processor 1440 to cause the device 1405 to perform various aspects of dataset generation for encoder training as described herein, or the at least one processor 1440 and the at least one memory 1430 may be otherwise configured to, individually or collectively, perform or support such operations.
[0202] FIG. 15 shows a flowchart illustrating a method 1500 that supports dataset generation for encoder training in accordance with one or more aspects of the present disclosure. The operations of the method 1500 may be implemented by a first network entity or its components as described herein. For example, the operations of the method 1500 may be performed by a first network entity as described with reference to FIGs. 1 through 10. In some examples, a first network entity may execute a set of instructions to control the functional elements of the first network entity to perform the described functions. Additionally, or alternatively, the first network entity may perform aspects of the described functions using special-purpose hardware.
[0203] At 1505, the method may include generating, at the first network entity, a first set of CSI data that is based on a second set of CSI data at the first network entity, the second set of CSI data being associated with a training of a first CSI decoder at the first network entity, where the first set of CSI data being a synthesized version of the second set of CSI data. The operations of 1505 may be performed in accordance with examples as disclosed herein. In some examples, aspects of the operations of 1505 may be performed by a CSI dataset generation component 925 as described with reference to FIG. 9.
[0204] At 1510, the method may include outputting, to a second network entity, the first set of CSI data for training a first CSI encoder at the second network entity. The operations of 1510 may be performed in accordance with examples as disclosed herein. In some examples, aspects of the operations of 1510 may be performed by a CSI dataset output component 930 as described with reference to FIG. 9.
[0205] At 1515, the method may include obtaining, from the second network entity, a first message based on outputting the first set of CSI data to the second network entity. The operations of 1515 may be performed in accordance with examples as disclosed herein. In some examples, aspects of the operations of 1515 may be performed by a first message acquisition component 935 as described with reference to FIG. 9.
[0206] FIG. 16 shows a flowchart illustrating a method 1600 that supports dataset generation for encoder training in accordance with one or more aspects of the present disclosure. The operations of the method 1600 may be implemented by a second network entity or its components as described herein. For example, the operations of the method 1600 may be performed by a second network entity as described with reference to FIGs. 1 through 6 and 11 through 14. In some examples, a second network entity may execute a set of instructions to control the functional elements of the second network entity to perform the described functions. Additionally, or alternatively, the second network entity may perform aspects of the described functions using special-purpose hardware.
[0207] At 1605, the method may include obtaining, from a first network entity, a set of parameters for a first CSI encoder at the first network entity and a set of information associated with an output of the first CSI encoder, the output of the first CSI encoder being based on a first set of CSI data at the first network entity. The operations of 1605 may be performed in accordance with examples as disclosed herein. In some examples, aspects of the operations of 1605 may be performed by a CSI encoder parameter and information acquisition component 1325 as described with reference to FIG. 13.
[0208] At 1610, the method may include generating, at the second network entity and in response to reception of the set of parameters and the set of information, a second set of CSI data for training a second CSI encoder at the second network entity, the second set of CSI data being based on the first set of CSI data and being a synthesized version of the first set of CSI data. The operations of 1610 may be performed in accordance with examples as disclosed herein. In some examples, aspects of the operations of 1610 may be performed by a CSI dataset generation component 1330 as described with reference to FIG. 13.
[0209] At 1615, the method may include training, at the second network entity and in response to generation of the second set of CSI data, the second CSI encoder using the second set of CSI data. The operations of 1615 may be performed in accordance with examples as disclosed herein. In some examples, aspects of the operations of 1615 may be performed by a CSI encoder training component 1335 as described with reference to FIG. 13.
[0210] At 1620, the method may include outputting, to the first network entity, a first message that is obtained via the second CSI encoder based on training the second CSI encoder using the second set of CSI data. The operations of 1620 may be performed in accordance with examples as disclosed herein. In some examples, aspects of the operations of 1620 may be performed by a first message transmission component 1340 as described with reference to FIG. 13.
[0211] The following provides an overview of aspects of the present disclosure:
[0212] Aspect 1: A method for wireless communications by a first network entity, comprising: generating, at the first network entity, a first set of CSI data that is based at least in part on a second set of CSI data at the first network entity, the second set of CSI data being associated with a training of a first CSI decoder at the first network entity, wherein the first set of CSI data being a synthesized version of the second set of CSI data; outputting, to a second network entity, the first set of CSI data for training a first CSI encoder at the second network entity; and obtaining, from the second network entity, a first message based at least in part on outputting the first set of CSI data to the second network entity.
[0213] Aspect 2: The method of aspect 1, wherein the second set of CSI data is associated with a first performance indication that is a function of a difference between the second set of CSI data and an output of a second CSI encoder at the first network entity and a second CSI decoder at the second network entity using the second set of CSI data, .
[0214] Aspect 3: The method of aspect 2, wherein the first set of CSI data is associated with a second performance indication that is a function of a difference between the first set of CSI data and an output of the second CSI encoder at the first network entity and the first CSI decoder at the first network entity using the first set of CSI data and generation of the first set of CSI data is based at least in part on the second performance indication satisfying one or more thresholds.
[0215] Aspect 4: The method of any of aspects 1 through 3, wherein generating the first set of CSI data comprises: generating, at the first network entity, the first set of CSI data based at least in part on the first set of CSI data satisfying a set of thresholds.
[0216] Aspect 5: The method of aspect 4, wherein the set of thresholds are key performance indicator thresholds.
[0217] Aspect 6: The method of any of aspects 4 through 5, wherein a first quantity of CSI data samples within the first set of CSI data that satisfy the set of thresholds is based at least in part on the second set of CSI data comprising a second quantity of CSI data samples that satisfy the set of thresholds.
[0218] Aspect 7: The method of any of aspects 1 through 6, wherein the first set of CSI data comprises a quantity of CSI data samples from a third set of CSI data.
[0219] Aspect 8: The method of aspect 7, wherein the first set of CSI data comprises the quantity of CSI data samples from the third set of CSI data based at least in part on the quantity of CSI data samples satisfying one or more respective threshold.
[0220] Aspect 9: The method of any of aspects 1 through 8, wherein the first set of CSI data is generated via a synthetic channel model, one or more random vectors, one or more random matrices, or any combination thereof.
[0221] Aspect 10: A method for wireless communications by a second network entity, comprising: obtaining, from a first network entity, a set of parameters for a first CSI encoder at the first network entity and a set of information associated with an output of the first CSI encoder, the output of the first CSI encoder being based at least in part on a first set of CSI data at the first network entity; generating, at the second network entity and in response to reception of the set of parameters and the set of information, a second set of CSI data for training a second CSI encoder at the second network entity, the second set of CSI data being based at least in part on the first set of CSI data and being a synthesized version of the first set of CSI data; training, at the second network entity and in response to generation of the second set of CSI data, the second CSI encoder using the second set of CSI data; and outputting, to the first network entity, a first message that is obtained via the second CSI encoder based at least in part on training the second CSI encoder using the second set of CSI data.
[0222] Aspect 11: The method of aspect 10, wherein obtaining the set of information associated with the output of the first CSI encoder comprises: obtaining, from the first network entity for one or more data samples within the first set of CSI data, an indication of one or more outputs of the first CSI encoder using the first set of CSI data, an indication of statistical information associated with the one or more outputs of the first CSI encoder using the first set of CSI data, or a combination thereof.
[0223] Aspect 12: The method of aspect 11, wherein generating the second set of CSI data comprises: generating a quantity of data samples that result in an output of the second CSI encoder being equal to the one or more outputs of the first CSI encoder using the first set of CSI data.
[0224] Aspect 13: The method of any of aspects 11 through 12, wherein generating the second set of CSI data comprises: selecting a quantity of data samples for the second set of CSI data from a third set of CSI data based at least in part on the output of the second CSI encoder using the quantity of data samples from the third set of CSI data being equal to the one or more outputs of the first CSI encoder using the first set of CSI data.
[0225] Aspect 14: The method of any of aspects 10 through 13, wherein the set of information associated with the output of the first CSI encoder is obtained based at least in part on the output of a first CSI decoder at the first network entity using the first set of CSI data satisfying one or more thresholds.
[0226] Aspect 15: The method of aspect 14, wherein the one or more thresholds are key performance indicator thresholds.
[0227] Aspect 16: The method of any of aspects 10 through 15, wherein the second set of CSI data is generated via a synthetic channel model, one or more random vectors, one or more random matrices, or any combination thereof.
[0228] Aspect 17: A first network entity for wireless communications, comprising one or more memories storing processor-executable code, and one or more processors coupled with the one or more memories and individually or collectively operable to execute the code to cause the first network entity to perform a method of any of aspects 1 through 9.
[0229] Aspect 18: A first network entity for wireless communications, comprising at least one means for performing a method of any of aspects 1 through 9.
[0230] Aspect 19: A non-transitory computer-readable medium storing code for wireless communications, the code comprising instructions executable by one or more processors to perform a method of any of aspects 1 through 9.
[0231] Aspect 20: A second network entity for wireless communications, comprising one or more memories storing processor-executable code, and one or more processors coupled with the one or more memories and individually or collectively operable to execute the code to cause the second network entity to perform a method of any of aspects 10 through 16.
[0232] Aspect 21: A second network entity for wireless communications, comprising at least one means for performing a method of any of aspects 10 through 16.
[0233] Aspect 22: A non-transitory computer-readable medium storing code for wireless communications, the code comprising instructions executable by one or more processors to perform a method of any of aspects 10 through 16.
[0234] It should be noted that the methods described herein describe possible implementations. The operations and the steps may be rearranged or otherwise modified and other implementations are possible. Further, aspects from two or more of the methods may be combined.
[0235] Although aspects of an LTE, LTE-A, LTE-A Pro, or NR system may be described for purposes of example, and LTE, LTE-A, LTE-A Pro, or NR terminology may be used in much of the description, the techniques described herein are applicable beyond LTE, LTE-A, LTE-A Pro, or NR networks. For example, the described techniques may be applicable to various other wireless communications systems such as Ultra Mobile Broadband (UMB) , Institute of Electrical and Electronics Engineers (IEEE) 802.11 (Wi-Fi) , IEEE 802.16 (WiMAX) , IEEE 802.20, Flash-OFDM, as well as other systems and radio technologies not explicitly mentioned herein.
[0236] Information and signals described herein may be represented using any of a variety of different technologies and techniques. For example, data, instructions, commands, information, signals, bits, symbols, and chips that may be referenced throughout the description may be represented by voltages, currents, electromagnetic waves, magnetic fields or particles, optical fields or particles, or any combination thereof.
[0237] The various illustrative blocks and components described in connection with the disclosure herein may be implemented or performed using a general-purpose processor, a DSP, an ASIC, a CPU, a graphics processing unit (GPU) , a neural processing unit (NPU) , an FPGA or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. A general-purpose processor may be a microprocessor but, in the alternative, the processor may be any processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices (e.g., a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration) . Any functions or operations described herein as being capable of being performed by a processor may be performed by multiple processors that, individually or collectively, are capable of performing the described functions or operations.
[0238] The functions described herein may be implemented using hardware, software executed by a processor, firmware, or any combination thereof. If implemented using software executed by a processor, the functions may be stored as or transmitted using one or more instructions or code of a computer-readable medium. Other examples and implementations are within the scope of the disclosure and appended claims. For example, due to the nature of software, functions described herein may be implemented using software executed by a processor, hardware, firmware, hardwiring, or combinations of any of these. Features implementing functions may also be physically located at various positions, including being distributed such that portions of functions are implemented at different physical locations.
[0239] Computer-readable media includes both non-transitory computer storage media and communication media including any medium that facilitates transfer of a computer program from one location to another. A non-transitory storage medium may be any available medium that may be accessed by a general-purpose or special-purpose computer. By way of example, and not limitation, non-transitory computer-readable media may include RAM, ROM, electrically erasable programmable ROM (EEPROM) , flash memory, compact disk (CD) ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other non-transitory medium that may be used to carry or store desired program code means in the form of instructions or data structures and that may be accessed by a general-purpose or special-purpose computer or a general-purpose or special-purpose processor. Also, any connection is properly termed a computer-readable medium. For example, if the software is transmitted from a website, server, or other remote source using a coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL) , or wireless technologies such as infrared, radio, and microwave, then the coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave are included in the definition of computer-readable medium. Disk and disc, as used herein, include CD, laser disc, optical disc, digital versatile disc (DVD) , floppy disk, and Blu-ray disc. Disks may reproduce data magnetically, and discs may reproduce data optically using lasers. Combinations of the above are also included within the scope of computer-readable media. Any functions or operations described herein as being capable of being performed by a memory may be performed by multiple memories that, individually or collectively, are capable of performing the described functions or operations.
[0240] As used herein, including in the claims, “or” as used in a list of items (e.g., a list of items prefaced by a phrase such as “at least one of” or “one or more of” ) indicates an inclusive list such that, for example, a list of at least one of A, B, or C means A or B or C or AB or AC or BC or ABC (i.e., A and B and C) . Also, as used herein, the phrase “based on” shall not be construed as a reference to a closed set of conditions. For example, an example step that is described as “based on condition A” may be based on both a condition A and a condition B without departing from the scope of the present disclosure. In other words, as used herein, the phrase “based on” shall be construed in the same manner as the phrase “based at least in part on. ”
[0241] As used herein, including in the claims, the article “a” before a noun is open-ended and understood to refer to “at least one” of those nouns or “one or more” of those nouns. Thus, the terms “a, ” “at least one, ” “one or more, ” and “at least one of one or more” may be interchangeable. For example, if a claim recites “a component” that performs one or more functions, each of the individual functions may be performed by a single component or by any combination of multiple components. Thus, the term “a component” having characteristics or performing functions may refer to “at least one of one or more components” having a particular characteristic or performing a particular function. Subsequent reference to a component introduced with the article “a” using the terms “the” or “said” may refer to any or all of the one or more components. For example, a component introduced with the article “a” may be understood to mean “one or more components, ” and referring to “the component” subsequently in the claims may be understood to be equivalent to referring to “at least one of the one or more components. ” Similarly, subsequent reference to a component introduced as “one or more components” using the terms “the” or “said” may refer to any or all of the one or more components. For example, referring to “the one or more components” subsequently in the claims may be understood to be equivalent to referring to “at least one of the one or more components. ”
[0242] The term “determine” or “determining” encompasses a variety of actions and, therefore, “determining” can include calculating, computing, processing, deriving, investigating, looking up (such as via looking up in a table, a database, or another data structure) , ascertaining, and the like. Also, “determining” can include receiving (e.g., receiving information) , accessing (e.g., accessing data stored in memory) , and the like. Also, “determining” can include resolving, obtaining, selecting, choosing, establishing, and other such similar actions.
[0243] In the appended figures, similar components or features may have the same reference label. Further, various components of the same type may be distinguished by following the reference label by a dash and a second label that distinguishes among the similar components. If just the first reference label is used in the specification, the description is applicable to any one of the similar components having the same first reference label irrespective of the second reference label or other subsequent reference label.
[0244] The description set forth herein, in connection with the appended drawings, describes example configurations and does not represent all the examples that may be implemented or that are within the scope of the claims. The term “example” used herein means “serving as an example, instance, or illustration” and not “preferred” or “advantageous over other examples. ” The detailed description includes specific details for the purpose of providing an understanding of the described techniques. These techniques, however, may be practiced without these specific details. In some figures, known structures and devices are shown in block diagram form in order to avoid obscuring the concepts of the described examples.
[0245] The description herein is provided to enable a person having ordinary skill in the art to make or use the disclosure. Various modifications to the disclosure will be apparent to a person having ordinary skill in the art, and the generic principles defined herein may be applied to other variations without departing from the scope of the disclosure. Thus, the disclosure is not limited to the examples and designs described herein but is to be accorded the broadest scope consistent with the principles and novel features disclosed herein.
Claims
1.A first network entity, comprising:one or more memories storing processor-executable code; andone or more processors coupled with the one or more memories and individually or collectively operable to execute the code to cause the first network entity to:generate, at the first network entity, a first set of channel state information (CSI) data that is based at least in part on a second set of CSI data at the first network entity, the second set of CSI data being associated with a training of a first CSI decoder at the first network entity, wherein the first set of CSI data being a synthesized version of the second set of CSI data;output, to a second network entity, the first set of CSI data for training a first CSI encoder at the second network entity; andobtain, from the second network entity, a first message based at least in part on outputting the first set of CSI data to the second network entity.2.The first network entity of claim 1, wherein the second set of CSI data is associated with a first performance indication that is a function of a difference between the second set of CSI data and an output of a second CSI encoder at the first network entity and the first CSI decoder at the first network entity using the second set of CSI data.3.The first network entity of claim 2, wherein the first set of CSI data is associated with a second performance indication that is a function of a difference between the first set of CSI data and an output of the second CSI encoder at the first network entity and the first CSI decoder at the first network entity using the first set of CSI data and generation of the first set of CSI data is based at least in part on the second performance indication satisfying one or more thresholds.4.The first network entity of claim 1, wherein, to generate the first set of CSI data, the one or more processors are individually or collectively operable to execute the code to cause the first network entity to:generate, at the first network entity, the first set of CSI data based at least in part on the first set of CSI data satisfying a set of thresholds.5.The first network entity of claim 4, wherein:the set of thresholds are key performance indicator thresholds.6.The first network entity of claim 4, wherein a first quantity of CSI data samples within the first set of CSI data that satisfy the set of thresholds is based at least in part on the second set of CSI data comprising a second quantity of CSI data samples that satisfy the set of thresholds.7.The first network entity of claim 1, wherein the first set of CSI data comprises a quantity of CSI data samples from a third set of CSI data.8.The first network entity of claim 7, wherein the first set of CSI data comprises the quantity of CSI data samples from the third set of CSI data based at least in part on the quantity of CSI data samples satisfying one or more respective threshold.9.The first network entity of claim 1, wherein the first set of CSI data is generated via a synthetic channel model, one or more random vectors, one or more random matrices, or any combination thereof.10.A second network entity, comprising:one or more memories storing processor-executable code; andone or more processors coupled with the one or more memories and individually or collectively operable to execute the code to cause the second network entity to:obtain, from a first network entity, a set of parameters for a first channel state information (CSI) encoder at the first network entity and a set of information associated with an output of the first CSI encoder, the output of the first CSI encoder being based at least in part on a first set of CSI data at the first network entity;generate, at the second network entity and in response to reception of the set of parameters and the set of information, a second set of CSI data for training a second CSI encoder at the second network entity, the second set of CSI data being based at least in part on the first set of CSI data and being a synthesized version of the first set of CSI data;training, at the second network entity and in response to generation of the second set of CSI data, the second CSI encoder used the second set of CSI data; andoutput, to the first network entity, a first message that is obtained via the second CSI encoder based at least in part on training the second CSI encoder using the second set of CSI data.11.The second network entity of claim 10, wherein, to obtain the set of information associated with the output of the first CSI encoder, the one or more processors are individually or collectively operable to execute the code to cause the second network entity to:obtain, from the first network entity for one or more data samples within the first set of CSI data, an indication of one or more outputs of the first CSI encoder using the first set of CSI data, an indication of statistical information associated with the one or more outputs of the first CSI encoder using the first set of CSI data, or a combination thereof.12.The second network entity of claim 11, wherein, to generate the second set of CSI data, the one or more processors are individually or collectively operable to execute the code to cause the second network entity to:generate a quantity of data samples that result in an output of the second CSI encoder being equal to the one or more outputs of the first CSI encoder using the first set of CSI data.13.The second network entity of claim 11, wherein, to generate the second set of CSI data, the one or more processors are individually or collectively operable to execute the code to cause the second network entity to:select a quantity of data samples for the second set of CSI data from a third set of CSI data based at least in part on the output of the second CSI encoder using the quantity of data samples from the third set of CSI data being equal to the one or more outputs of the first CSI encoder using the first set of CSI data.14.The second network entity of claim 10, wherein the set of information associated with the output of the first CSI encoder is obtained based at least in part on the output of a first CSI decoder at the first network entity using the first set of CSI data satisfying one or more thresholds.15.The second network entity of claim 14, wherein:the one or more thresholds are key performance indicator thresholds.16.The second network entity of claim 10, wherein the second set of CSI data is generated via a synthetic channel model, one or more random vectors, one or more random matrices, or any combination thereof.17.A method for wireless communications by a second network entity, comprising:obtaining, from a first network entity, a set of parameters for a first channel state information (CSI) encoder at the first network entity and a set of information associated with an output of the first CSI encoder, the output of the first CSI encoder being based at least in part on a first set of CSI data at the first network entity;generating, at the second network entity and in response to reception of the set of parameters and the set of information, a second set of CSI data for training a second CSI encoder at the second network entity, the second set of CSI data being based at least in part on the first set of CSI data and being a synthesized version of the first set of CSI data;training, at the second network entity and in response to generation of the second set of CSI data, the second CSI encoder using the second set of CSI data; andoutputting, to the first network entity, a first message that is obtained via the second CSI encoder based at least in part on training the second CSI encoder using the second set of CSI data.18.The method of claim 17, wherein obtaining the set of information associated with the output of the first CSI encoder comprises:obtaining, from the first network entity for one or more data samples within the first set of CSI data, an indication of one or more outputs of the first CSI encoder using the first set of CSI data, an indication of statistical information associated with the one or more outputs of the first CSI encoder using the first set of CSI data, or a combination thereof.19.The method of claim 17, wherein the set of information associated with the output of the first CSI encoder is obtained based at least in part on the output of a first CSI decoder at the first network entity using the first set of CSI data satisfying one or more thresholds.20.The method of claim 17, wherein the second set of CSI data is generated via a synthetic channel model, one or more random vectors, one or more random matrices, or any combination thereof.