Channel state information encoding model structure
By standardizing the feature-extracting component type and hyperparameters for CSI encoders, the method ensures interoperability and enhances the accuracy of CSI decoding in wireless communications 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 communications systems face challenges in ensuring interoperability and accurate decoding of channel state information (CSI) feedback due to the use of different AI or ML model components and hyperparameters between encoding and decoding devices.
A method for wireless communications that involves obtaining and applying a feature-extracting component type and hyperparameters for a CSI encoder, allowing for consistent encoding and decoding using transformer-based, MLP mixer-based, or CNN-based models, ensuring compatibility and improved performance.
Enhances the flexibility and configurability of CSI feedback, enabling devices to provide consistent input and output information, thereby improving the accuracy of CSI decoding compared to codebook-based methods.
Smart Images

Figure CN2024130705_15052026_PF_FP_ABST
Abstract
Description
CHANNEL STATE INFORMATION ENCODING MODEL STRUCTURE
[0001] FIELD OF TECHNOLOGY
[0002] The following relates to wireless communications, including channel state information (CSI) encoding model structure.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) . Devices may communicate channel state information (CSI) .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 obtaining, from a second network entity, a first message including an indication of a feature-extracting component type for a machine learning model of a channel state information (CSI) encoder, one or more hyperparameters for the machine learning model, or both, encoding CSI via the CSI encoder, where the CSI encoder is based on the one or more hyperparameters, includes a feature-extracting component of the indicated feature-extracting component type, or both, and outputting, to the second network entity, a second message that is obtained via the CSI encoder at the first 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 obtain, from a second network entity, a first message including an indication of a feature-extracting component type for a machine learning model of a CSI encoder, one or more hyperparameters for the machine learning model, or both, encode CSI via the CSI encoder, where the CSI encoder is based on the one or more hyperparameters, includes a feature-extracting component of the indicated feature-extracting component type, or both, and output, to the second network entity, a second message that is obtained via the CSI encoder at the first network entity.
[0007] Another first network entity for wireless communications is described. The first network entity may include means for obtaining, from a second network entity, a first message including an indication of a feature-extracting component type for a machine learning model of a CSI encoder, one or more hyperparameters for the machine learning model, or both, means for encoding CSI via the CSI encoder, where the CSI encoder is based on the one or more hyperparameters, includes a feature-extracting component of the indicated feature-extracting component type, or both, and means for outputting, to the second network entity, a second message that is obtained via the CSI encoder at the first 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 obtain, from a second network entity, a first message including an indication of a feature-extracting component type for a machine learning model of a CSI encoder, one or more hyperparameters for the machine learning model, or both, encode CSI via the CSI encoder, where the CSI encoder is based on the one or more hyperparameters, includes a feature-extracting component of the indicated feature- extracting component type, or both, and output, to the second network entity, a second message that is obtained via the CSI encoder at the first network entity.
[0009] In some examples of the method, first network entities, and non-transitory computer-readable medium described herein, the feature-extracting component type comprises a transformer-based feature extracting component type, and the one or more hyperparameters include the feature-extracting component, a quantity of modules of the feature-extracting component, a dimension of an input to the feature-extracting component, a dimension of one or more first layers of each first module of a set of multiple first modules of the feature-extracting component, a quantity of calculations in each first module of the set of multiple first modules, a dimension of a set of multiple calculations in the set of multiple first modules, a dimension of one or more second layers of each second module of a set of multiple second modules of the feature-extracting component, a quantity of tokens, a compression identifier, or any combination thereof.
[0010] In some examples of the method, first network entities, and non-transitory computer-readable medium described herein, the feature-extracting component type comprises a multilayer perceptron (MLP) mixer-based feature extracting component type, and the one or more hyperparameters include the feature-extracting component, a quantity of modules of the feature-extracting component, a dimension of an input to the feature-extracting component, a dimension of one or more first layers of each first module of a set of multiple first modules, a dimension of one or more second layers of each second module of a set of multiple second modules, a compression identifier, or any combination thereof.
[0011] In some examples of the method, first network entities, and non-transitory computer-readable medium described herein, the feature-extracting component type comprises a convolutional neural network (CNN) -based feature extracting component type, and the one or more hyperparameters include the feature-extracting component, a dimension of an input to the feature-extracting component, a quantity of modules of the feature-extracting component, a kernel size of a first layer at a beginning of the CSI encoder, a stride of the first layer at the beginning of the CSI encoder, a quantity of layers within each of a set of multiple modules, a dimension of an output within the set of multiple modules, a kernel size of the quantity of layers of each of the set of multiple modules, a stride of the quantity of layers of each of the set of multiple modules, or any combination thereof.
[0012] Some examples of the method, first network entities, and non-transitory computer-readable medium described herein may further include operations, features, means, or instructions for outputting, prior to obtaining the indication of the feature-extracting component type and the one or more hyperparameters, a capability message indicating a capability of the first network entity to support one or more model structures, the one or more model structures including different combinations of feature-extracting component types and hyperparameters, where the feature-extracting component type and the one or more hyperparameters may be in accordance with the capability message.
[0013] In some examples of the method, first network entities, and non-transitory computer-readable medium described herein, the first message further includes one or more model parameters and encoding the CSI may be based on the one or more model parameters.
[0014] In some examples of the method, first network entities, and non-transitory computer-readable medium described herein, the one or more hyperparameters may be external to the machine learning model and values of the one or more hyperparameters may be set prior to training the machine learning model.
[0015] In some examples of the method, first network entities, and non-transitory computer-readable medium described herein, the one or more hyperparameters may be indicated separately.
[0016] In some examples of the method, first network entities, and non-transitory computer-readable medium described herein, the one or more hyperparameters may be indicated as a combination, the combination being one of a set of multiple combinations of predefined hyperparameters.
[0017] In some examples of the method, first network entities, and non-transitory computer-readable medium described herein, the second message includes a latent message.
[0018] In some examples of the method, first network entities, and non-transitory computer-readable medium described herein, the feature-extracting component type, the one or more hyperparameters, or both may be applied directly to the CSI encoder that may be used to encode the CSI.
[0019] Some examples of the method, first network entities, and non-transitory computer-readable medium described herein may further include operations, features, means, or instructions for obtaining, via the first message, the feature-extracting component type, the one or more hyperparameters, or both that may be indicative of a mapping between an input to the CSI encoder and an output of the CSI encoder and training the machine learning model of the CSI encoder using the mapping, where encoding the CSI may be based on the trained model.
[0020] 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
[0021] FIGs. 1 and 2 show examples of wireless communications systems that support channel state information (CSI) encoding model structures in accordance with one or more aspects of the present disclosure.
[0022] FIG. 3 shows an example of a transformer-based feature-extraction component that supports CSI encoding model structure in accordance with one or more aspects of the present disclosure.
[0023] FIG. 4 shows an example of a multilayer perceptron (MLP) mixer-based feature extracting component that supports CSI encoding model structure in accordance with one or more aspects of the present disclosure.
[0024] FIG. 5 shows an example of a convolutional neural network (CNN) -based feature extracting component that supports CSI encoding model structure in accordance with one or more aspects of the present disclosure.
[0025] FIG. 6 shows an example of a process flow that supports CSI encoding model structure in accordance with one or more aspects of the present disclosure.
[0026] FIGs. 7 and 8 show block diagrams of devices that support CSI encoding model structure in accordance with one or more aspects of the present disclosure.
[0027] FIG. 9 shows a block diagram of a communications manager that supports CSI encoding model structure in accordance with one or more aspects of the present disclosure.
[0028] FIG. 10 shows a diagram of a system including a device that supports CSI encoding model structure in accordance with one or more aspects of the present disclosure.
[0029] FIGs. 11 and 12 show flowcharts illustrating methods that support CSI encoding model structure in accordance with one or more aspects of the present disclosure.DETAILED DESCRIPTION
[0030] Devices may provide channel state information (CSI) feedback. For example, devices, including network entities, user equipments (UEs) , and the like may generate CSI feedback based on a CSI report configuration. In some cases, the CSI report configuration may include a codebook used as a precoding matrix indicator (PMI) dictionary. A device may report one or more PMI codewords (e.g., “best” codewords) from the PMI dictionary and use a sequence of bits to report a PMI. In other words, the device may identify, from the PMI dictionary, one or more codewords that are in accordance with channel measurements or channel conditions detected by the device. The device may include the identified one or more codewords in a CSI report, such as via the sequence of bits. Alternatively, the device may use an artificial intelligence (AI) or machine learning (ML) model to generate the CSI feedback.
[0031] For example, the device may use, alternatively to a PMI searching algorithm, a CSI encoder that includes an AI or ML model. Similarly, a receiving device may use a CSI decoder that includes an AI or ML model alternatively to the codebook. However, without collaboration between encoding and decoding devices, the encoding and decoding devices may not be compatible or interoperable with respect to the AI or ML model. That is, when the encoding and decoding devices use different AI or ML model components, different input parameters, different hyperparameters, or the like, the decoding device may not be able to accurately decode the CSI. Accordingly, techniques described herein support coordination of an AI or ML model structure.
[0032] As described herein, a first device (e.g., a first network entity or a UE) may obtain a first message including an indication of a feature-extracting component type for an ML model of a CSI encoder, one or more hyperparameters for the ML model, or both. In some examples, the feature-extracting component type may be known as model backbone type. The feature-extracting component type may refer to a transformer-based feature extracting component, a multilayer perceptron (MLP) mixer-based feature extracting component, or a convolutional neural network (CNN) -based feature extracting component type as described herein. The first device may apply the feature-extracting component of the indicated feature-extracting component type in the CSI encoder based on the first message.
[0033] Additionally, or alternatively, the one or more hyperparameters may correspond to a type of feature-extracting component of the CSI encoder (e.g., indicated by the first message or preconfigured) . For example, the type of feature-extracting component may have one or more related hyperparameters, and the first message may indicate some of those one or more related hyperparameters. The hyperparameters may be external to the ML model, and values of the one or more hyperparameters may be set prior to training the ML model.
[0034] The first device may output a second message that is obtained via the CSI encoder to a second device (e.g., a second network entity) . By using the AI or ML model to encode and decode CSI feedback, techniques described herein may be associated with improved performance compared to codebook-based CSI feedback. For example, the AI or ML model may support flexibility and configurability with respect to input and output information, which may allow devices to provide different CSI. Additionally, by configuring the AI or ML models using same parameters or training data at encoding and decoding devices, the AI or ML models may enable an output of a decoder to be more similar to an input of an encoder compared to the codebook-based CSI.
[0035] Aspects of the disclosure are initially described in the context of wireless communications systems. Aspects of the disclosure are also described in the context of transformer-based, MLP mixer-based, and CNN-based feature-extraction components 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 channel measurement encoding model structure.
[0036] FIG. 1 shows an example of a wireless communications system 100 that supports CSI encoding model structure 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.
[0037] 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) .
[0038] 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.
[0039] 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.
[0040] 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.
[0041] 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) .
[0042] 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) ) .
[0043] 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.
[0044] 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.
[0045] For instance, an access network (AN) or RAN may include communications between access nodes (e.g., an IAB donor) , IAB node (s) 104, and one or more UEs 115. The IAB donor may facilitate connection between the core network 130 and the AN (e.g., via a wired or wireless connection to the core network 130) . That is, an IAB donor may refer to a RAN node with a wired or wireless connection to the core network 130. The IAB donor may include one or more of a CU 160, a DU 165, and an RU 170, in which case the CU 160 may communicate with the core network 130 via an interface (e.g., a backhaul link) . The IAB donor and IAB node (s) 104 may communicate via an F1 interface according to a protocol that defines signaling messages (e.g., an F1 AP protocol) . Additionally, or alternatively, the CU 160 may communicate with the core network 130 via an interface, which may be an example of a portion of a backhaul link, and may communicate with other CUs (e.g., including a CU 160 associated with an alternative IAB donor) via an Xn-C interface, which may be an example of another portion of a backhaul link.
[0046] IAB node (s) 104 may refer to RAN nodes that provide IAB functionality (e.g., access for UEs 115, wireless self-backhauling capabilities) . A DU 165 may act as a distributed scheduling node towards child nodes associated with the IAB node (s) 104, and the IAB-MT may act as a scheduled node towards parent nodes associated with IAB node (s) 104. That is, an IAB donor may be referred to as a parent node in communication with one or more child nodes (e.g., an IAB donor may relay transmissions for UEs through other IAB node (s) 104) . Additionally, or alternatively, IAB node (s) 104 may also be referred to as parent nodes or child nodes to other IAB node (s) 104, depending on the relay chain or configuration of the AN. The IAB-MT entity of IAB node (s) 104 may provide a Uu interface for a child IAB node (e.g., the IAB node (s) 104) to receive signaling from a parent IAB node (e.g., the IAB node (s) 104) , and a DU interface (e.g., a DU 165) may provide a Uu interface for a parent IAB node to signal to a child IAB node or UE 115.
[0047] For example, IAB node (s) 104 may be referred to as parent nodes that support communications for child IAB nodes, or may be referred to as child IAB nodes associated with IAB donors, or both. An IAB donor may include a CU 160 with a wired or wireless connection (e.g., backhaul communication link (s) 120) to the core network 130 and may act as a parent node to IAB node (s) 104. For example, the DU 165 of an IAB donor may relay transmissions to UEs 115 through IAB node (s) 104, or may directly signal transmissions to a UE 115, or both. The CU 160 of the IAB donor may signal communication link establishment via an F1 interface to IAB node (s) 104, and the IAB node (s) 104 may schedule transmissions (e.g., transmissions to the UEs 115 relayed from the IAB donor) through one or more DUs (e.g., DUs 165) . That is, data may be relayed to and from IAB node (s) 104 via signaling via an NR Uu interface to MT of IAB node (s) 104 (e.g., other IAB node (s) ) . Communications with IAB node (s) 104 may be scheduled by a DU 165 of the IAB donor or of IAB node (s) 104.
[0048] 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 CSI encoding model structure 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) .
[0049] 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.
[0050] 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.
[0051] 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) .
[0052] 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.
[0053] 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) .
[0054] 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.
[0055] 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) ) .
[0056] 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) .
[0057] 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.
[0058] 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.
[0059] 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.
[0060] 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.
[0061] 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.
[0062] 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.
[0063] 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.
[0064] The network entities 105 or the UEs 115 may use MIMO communications to exploit multipath signal propagation and increase spectral efficiency by transmitting or receiving multiple signals via different spatial layers. Such techniques may be referred to as spatial multiplexing. The multiple signals may, for example, be transmitted by the transmitting device via different antennas or different combinations of antennas. Likewise, the multiple signals may be received by the receiving device via different antennas or different combinations of antennas. Each of the multiple signals may be referred to as a separate spatial stream and may carry information associated with the same data stream (e.g., the same codeword) or different data streams (e.g., different codewords) . Different spatial layers may be associated with different antenna ports used for channel measurement and reporting. MIMO techniques include single-user MIMO (SU-MIMO) , for which multiple spatial layers are transmitted to the same receiving device, and multiple-user MIMO (MU-MIMO) , for which multiple spatial layers are transmitted to multiple devices.
[0065] 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) .
[0066] Certain aspects and techniques as described herein may be implemented, at least in part, using an AI program, such as a program that includes a 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.
[0067] 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 CSI encoding. Thus, during operation of a device, the ML model may receive input data (e.g., channel quality measurements, precoder matrix, rank information) and make inferences (e.g., a compressed CSI report) based on the weights and biases.
[0068] ML models may be deployed in one or more devices (for example, network entities 105 and UEs 115) 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.
[0069] 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 ML 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.
[0070] 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 encode CSI. 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.
[0071] A network entity 105 may obtain a first message including an indication of a feature-extracting component type for a ML model of a CSI encoder, one or more hyperparameters for the ML model, or both. The network entity 105 may encode CSI via the CSI encoder, where the CSI encoder is based on the one or more hyperparameters, includes a feature-extracting component of the indicated feature-extracting component type, or both. The network entity 105 may output a second message that is obtained via the CSI encoder at the network entity 105.
[0072] FIG. 2 shows an example of a wireless communications system 200 that supports CSI encoding model structure in accordance with one or more aspects of the present disclosure. The wireless communications system 200 may implement or be implemented by the wireless communications system 100. For example, the wireless communications system 200 may include a network entity 105-a and a network entity 105-b, which may be examples of corresponding devices as described with reference to FIG. 1.
[0073] The network entity 105-a and the network entity 105-b may communicate CSI, including CSI feedback. The network entity 105-a and the network entity 105-b may be examples of collocated devices communicating via wireless or wired connections. That is, the network entity 105-a and the network entity 105-b may be units of a same network entity (e.g., CUs, DUs, RUs, etc. ) . Alternatively, the network entity 105-a may be a UE while the network entity 105-b may be a network entity, such as the UE 115 and the network entity 105 described with reference to FIG. 1. In such examples, the network entity 105-a and the network entity 105-b may communicate wirelessly, such as via uplink and downlink communications links.
[0074] The network entity 105-a may include an encoder 205. As used herein, “encoding device” may refer to a device that includes an encoder 205 and encodes a message. For example, the network entity 105-a may be an encoding device in accordance with the network entity 105-a encoding CSI via the encoder 205 and outputting the encoded CSI.
[0075] The network entity 105-b may include a decoder 210. As used herein, “decoding device” may refer to a device that includes a decoder 210 and decodes a message. For example, the network entity 105-b may be a decoding device in accordance with the network entity 105-b decoding CSI via the decoder 210 and obtaining the decoded CSI. Techniques described herein for CSI encoding may be understood to be applicable to decoding the CSI, where the decoding occurs in a reverse order from the encoding. For example, portions of encoding procedures described with reference to FIGs. 3 through 5 may be performed by decoding devices, such as the network entity 105-b, in a reverse order to obtain decoded CSI.
[0076] The network entity 105-a may obtain encoder information 215 from the network entity 105-b. The encoder information 215 may include parameters for the encoder 205, including model parameters, hyperparameters, feature-extracting component types, training data, or the like. The network entity 105-a may apply the encoder information 215 to the encoder 205 or otherwise use the encoder information 215 for the encoder 205. That is, the encoder 205 may be based on the encoder information 215. The encoder information 215 may include hyperparameters or a feature-extracting component type (e.g., model backbone type) . In some examples, the encoder information may also include model encoder parameters or weights that fit in the hyperparameter or a feature-extracting component type. In some examples, the encoder 205 may use the parameters or weights and transferred hyperparameters or a feature-extracting component type to generate the relationship between the input and output of the encoder, then use the input and output of the encoder to develop their actual encoder to be used in actual deployment. In some other examples, the encoder 205 may implement the model parameters or weights together with the hyperparameters or the feature-extracting component type as the actual encoder. In some cases, the first message transmitted from the network entity 105-b to the network entity 105-a may be regarding the information of the CSI encoder. In some other cases, the first message may include the information (e.g., hyperparameter or feature-extracting component type) of the CSI decoder. In this case, network entity 105-a may develop their actual decoder compatible or interoperable with the CSI decoder. In some cases, one or more model structure may be predefined (e.g., standardized in a standardization) . The information of hyperparameters or feature-extraction type may be regarding configuring the hyperparameters or feature-extraction type for the predefined (e.g., standardized) model structure. For example, there may be two model structures predefined, such as a CNN-based and transformer-based model structures. The configuration of feature-extraction type may be to configure whether CNN-based structure or transformer-based structure is used. Moreover, the configuration of hyperparameters may be to configure the hyperparameters of the selected structure..
[0077] In some implementations, ML models may include model parameters and model hyperparameters and model backbone (e.g., feature-extracting component type) . Model parameters are parameters that the model learns itself and model hyperparameters are parameters that are unlearnable from data associated with the ML models. In some instances, a model parameter may be described as a variable that is internal to a ML model (or any other model) and the value of the model parameter may be trained to be adapted to the data associated with the ML model. In some examples, a model parameter may be learned from the data. Such model parameters may also be based on historical training data. On the other hand, model hyperparameters may be a configuration that is external to the model and the value of a model hyperparameter cannot be estimated from data associated with the ML model. That is, a model hyperparameter may be described as a parameter whose value is set before training begins. In some examples, model hyperparameters may be set using one or more heuristics and are often tuned for a given modeling problem. In some examples, hyperparameter tuning may be used to create a ML model. As described herein, model hyperparameters are not learnable from the data, and a data scientist may have to set the model hyperparameters. In one example of building a deep neural network, the model hyperparameters may include a number of layers included in the deep neural network, a number of cells included in the deep neural network, or any combination.
[0078] The network entity 105-a may provide an input 220 to the encoder 205. The input may include, as an example, a downlink channel matrix H, downlink precoders V, an interference covariance matrix Rnn, or the like. The input 220 may include channel measurements or information that are used to generate CSI. The CSI may include information ranging from rank indicators (RIs) , PMIs, channel quality indicators (CQIs) , or any combination thereof to full channel information. The network entity 105-a may encode the input 220 via the encoder 205. The network entity 105-a may output an encoded message 230 including CSI to the network entity 105-b.
[0079] The network entity 105-b may obtain an output 225 using the decoder 210. For example, the network entity 105-b may generate an output 225 by providing the encoded message 230 to the decoder 210. The output 225 may include the downlink channel matrix H, a transmit covariance matrix, the downlink precoders V, the interference covariance matrix Rnn, a raw vs. whitened downlink channel, or the like.
[0080] In some examples, the input 220 may correspond to the output 225. For example, the input 220 may correspond to the output 225 according to Table 1 below, where H or V may correspond to a raw channel or a channel pre-whitened by the network entity 105-a based on a demodulation filter of the network entity 105-a.
[0081] Table 1
[0082] The encoder 205, the decoder 210, or both may include one or more components (e.g., AI or ML model components) that support CSI encoding and decoding. For example, the encoder 205, the decoder 210, or both may include a feature-extracting component (e.g., a common backbone) and one or more adaptation layers prior to the feature-extracting component (e.g., front-end multi-branch) , after the feature-extracting component (e.g., back-end multi-branch) , or both. The one or more adaptation layers may be of a type, such as of a branch family. In some examples, a first branch family (e.g., branch family 1) may be used to support variable antenna configurations, while a second branch family (e.g., branch family 2) may be used to support variable subband configurations, variable rank configurations, or variable payload configurations.
[0083] The one or more adaptation layers prior to the feature-extracting component may include one or more linear embeddings (e.g., linear-embedding 1, linear-embedding 2, etc. ) . The one or more linear embeddings may correspond to different configurations, such as different antenna setups or antenna setup groups (e.g., antenna setup or antenna setup group 1, antenna setup or antenna setup group 2, etc. ) . The one or more adaptation layers that are prior to the feature-extracting component may be adapted to a size or dimension of the input 220. For example, the encoder 205 may use the one or more adaptation layers to transform the size or dimension of the input 220 to a size or dimension of the feature-extracting component. In other words, the encoder 205 may, via the one or more adaptation layers prior to the feature-extracting component, transform the input 220 from a transmit domain to a feature domain (e.g., Nt *d_model, N_patch = Nsb *#layer, where each patch is a Nt *1 vector) .
[0084] The feature-extracting component (e.g., common backbone) may include or perform different features or operations based on a feature-extracting component type. The feature-extracting component types may be described in greater detail elsewhere herein, including with reference to FIGs. 3 through 5. The feature-extracting component may extract deep features with positional encoding (e.g., input = d_model, output = d_model, N_patch = Nsb *#layer, where each patch is a D_model *1 vector) .
[0085] The one or more adaptation layers after the feature-extracting component may include one or more linear compressions (e.g., linear-compression 1, linear-compression 2, etc. ) . The one or more linear compressions may correspond to different configurations, such as different subband configurations, ranks, antenna configurations, or payload configurations. The one or more adaptation layers that are after to the feature-extracting component may compress features extracted by the feature-extracting component across frequency and layers (e.g., (d_model *N_patch) *d_z or (d_model * N_sb) *d_z applied to all layers) .
[0086] FIG. 3 shows an example of a transformer-based feature-extraction component 300 that supports CSI encoding model structure in accordance with one or more aspects of the present disclosure. The transformer-based feature-extraction component 300 may implement or be implemented by the wireless communications system 100, the wireless communications system 200, or both. For example, the transformer-based feature-extraction component 300 may be implemented in a ML model of a CSI encoder at a network entity, which may be an example of the network entity 105-a as described with reference to FIG. 2.
[0087] In the example of FIG. 3, a network entity may configure a feature-extraction component (e.g., a model backbone) as transformer-based with one or more hyperparameters. The one or more hyperparameters may be configured separately (e.g., one-by-one) or jointly as a combination. For example, there may be a quantity (e.g., N) of candidate combinations of hyperparameters which the network entity may select from. In other words, the network entity may select a combination from multiple combinations of hyperparameters for the transformer-based feature-extraction component and configure the combination, where the combination includes the one or more hyperparameters.
[0088] The transformer-based feature extracting component may be referred to as a transformer encoder. In the example of FIG. 3, s may represent a MIMO stream index (e.g., s=1, 2, 3, or 4 for Rank 4 MIMO) . Additionally, N may represent a quantity of precoding vectors to compress for each MIMO stream. D-dimensional embedding vectors for an n-th input token that represents an n-th precoding vector for an s-th MIMO stream may be represented as and A D-dimensional task embedding vector for the s-th MIMO stream that is output from the l-th transformer encoder layer may be represented as ts, l. A matrix of token embeddings at an output of the l-th transformer encoder layer may be denoted by where xs, l (l = 1, 2, …, L) denotes a set of token embeddings at the output of the l-th transformer encoder layer in the transformer encoder, and where xs, 0 denotes a set of token embeddings at the input to the transformer encoder. A positional encoding component may transform the vectors to the vectors and provide the vectors as input to the transformer encoder along with the vector ts, 0. The transformer encoder may transform the vector ts, 0 and the vectors to the vector ts, L and the vectors
[0089] The transformer module of transformer-based feature-extraction model may include an attention module 305 and a feedforward module 310. It may be understood that the transformer-based feature-extraction component 300 may include more than one transformer module, where the quantity of transformer modules corresponds to a depth. The attention module 305 may obtain, as input, a cross product of one or more patches and a dimension (e.g., n_patch x d_model) . At 315, the attention module 305 may perform, for a fully connected (FC) layer, query, key, and value generation (e.g., FC (d_model *attn_inner_dim *3) ) . At 320, the attention module 305 may apply an attention mechanism across patches. At 325, the attention module 305 may perform multiplication. Each of tensors q, k, and v may be of size num_head *n_patch * (attn_inner_dim / num_head) . The multiplication may generate an output of dimension n_patch *ann_inner_dim / num_head. At 330, the attention module 305 may perform a projection out for the FC layer (e.g., FC (d_model*attn_inner_dim) ) . An output of the projection out may be n_patch *d_model. The attention module 305 may repeat 315 through 330 for each layer of multiple layers.
[0090] The feedforward module 310 may determine, at 355, d_model * ff_inner_dim for an FC layer, where a dimension of the output is n_patch * ff_inner_dim. At 340, the feedforward module 310 may determine a Gaussian error linear unit (Gelu) . At 345, the feedforward module 310 may determine ff_inner_dim * d_model, where the dimension of the output is n_patch *d_model. At 350, the feedforward module 310 may perform layer normalization. The feedforward module 310 may repeat 335 to 350 for each layer of multiple layers.
[0091] The transformer-based feature-extraction component may apply a compression layer at 355. A quantity of tokens Num_token out of a total n_patch embeddings may be used for compression. The compression layer may be applied to all the output tokens jointly, or apply to each token separately where the compression layer can be token-common or token-specific.
[0092] Table 2 includes examples of hyperparameters that may be applied to a CSI encoder (e.g., an ML model of the CSI encoder) . The configuration may include one or more parameters from the table.
[0093] Table 2
[0094] FIG. 4 shows an example of a MLP mixer-based feature-extraction component 400 that supports CSI encoding model structure in accordance with one or more aspects of the present disclosure. The MLP mixer-based feature-extraction component 400 may implement or be implemented by the wireless communications system 100, the wireless communications system 200, or both. For example, the MLP mixer-based feature-extraction component 400 may be implemented in a ML model of a CSI encoder at a network entity, which may be an example of the network entity 105-a as described with reference to FIG. 2.
[0095] In the example of FIG. 4, a network entity may configure a feature-extraction component (e.g., a model backbone) as an MLP mixer-based with one or more hyperparameters. The one or more hyperparameters may be configured separately (e.g., one-by-one) or jointly as a combination. For example, there may be a quantity (e.g., N) of candidate combinations of hyperparameters which the network entity may select from. In other words, the network entity may select a combination from multiple combinations of hyperparameters for the MLP mixer-based feature-extraction component and configure the combination, where the combination includes the one or more hyperparameters.
[0096] The MLP mixer module of MLP mixer-based feature-extraction component may include a patch-mixing module 405 and a spatial-mixing module 410. It may be understood that the MLP-mixer-based feature-extraction component 500 may include more than one MLP-mixer module, where the quantity of MLP-mixer modules corresponds to a depth. The patch-mixing module 405 may obtain, as input, a cross product of one or more patches and a dimension (e.g., n_patch x d_model) . At 415, the patch-mixing module 405 includes a 1-dimensional convolutional layer Conv1d (n_patch, patch_inner_dim, kernel_size=1) , where an output of 415 may have a dimension of patch_inner_dim *d_model. At 420, the patch-mixing module 405 may include an activation layer Gelu. At 425, the patch-mixing module 405 may include another 1-dimensional convolutional layer Conv1d (patch_inner_dim, num_patch, kernel_size=1) , where an output of 425 may have a dimension of n_patch*d_model. At 430, the patch-mixing module 405 may perform layer normalization. The patch-mixing module 405 may repeat 415 to 430 for each layer of multiple layers.
[0097] At 435, the spatial-mixing module 410 may include a fully connected layer FC (d_model *spa_inner_dim) , where an output of 435 may have a dimension of n_patch *spa_inner_dim. At 440, the spatial-mixing module 410 may include an activation layer Gelu. At 445, the spatial-mixing module 410 may determine another fully connection layer FC (spa_inner_dim *d_model) , where an output of 445 may have a dimension of n_patch *d_model. At 450, the spatial-mixing module 410 may perform layer normalization.
[0098] The MLP mixer-based feature-extraction component may apply a compression layer at 455. A quantity of tokens Num_token out of a total n_patch embeddings may be used for compression. The compression layer may be applied to all the output tokens jointly, or apply to each token separately where the compression layer can be token-common or token-specific.
[0099] Table 3 includes examples of hyperparameters that may be applied to a CSI encoder (e.g., an ML model of the CSI encoder) . The configuration may include one or more parameters from the table.
[0100] Table 3
[0101] FIG. 5 shows an example of a CNN-based feature-extraction component 500 that supports CSI encoding model structure in accordance with one or more aspects of the present disclosure. The CNN-based feature-extraction component 500 may implement or be implemented by the wireless communications system 100, the wireless communications system 200, or both. For example, the CNN-based feature-extraction component 500 may be implemented in a ML model of a CSI encoder at a network entity, which may be an example of the network entity 105-a as described with reference to FIG. 2.
[0102] In the example of FIG. 5, a network entity may configure a feature-extraction component (e.g., a model backbone) as an CNN-based with one or more hyperparameters. The one or more hyperparameters may be configured separately (e.g., one-by-one) or jointly as a combination. For example, there may be a quantity (e.g., N) of candidate combinations of hyperparameters which the network entity may select from. In other words, the network entity may select a combination from multiple combinations of hyperparameters for the CNN-based feature-extraction component and configure the combination, where the combination includes the one or more hyperparameters.
[0103] The CNN-based feature-extraction component 500 in the example of FIG. 5 may include a single CNN module 510. It may be understood that the CNN-based feature-extraction component 500 may include more than one CNN module, where the quantity of CNN modules corresponds to a depth. Additionally, the CNN-based feature-extraction component 500 in the example of FIG. 5 may include three inner layers. However, it may be understood that greater than or less than three inner layers may be included in the CNN module.
[0104] At 505, and at an adaptation layer, the CNN-based feature-extraction component 500 may include a convolution layer Conv (input_dim, d_model, keral_sz_1, stride_1) which adapts the input to the dimension of the CNN module. The CNN-based feature-extraction component module 510 may include, at 515 and for CNN layer 1, Conv (d_model, inner_dim, keral_sz_inner, stride_inner) , which adapts the dimension to the inner dimension of the CNN module. At 520, the CNN module 510 may include, for CNN layer 2, Conv (Inner_dim, Inner_dim, keral_sz_inner, stride_inner) to further extract deeper feature space. At 525, the CNN module 510 may determine, for CNN layer 3, Conv (Inner_dim, d_model keral_sz_inner, stride_inner) which adapts the dimension to the original input (e.g., dimension of CNN module) .
[0105] Table 4 includes examples of hyperparameters that may be applied to a CSI encoder (e.g., an ML model of the CSI encoder) . The configuration may include one or more hyperparameters from the table.
[0106] Table 4
[0107] In some cases, the configuration of the hyperparameters shown in Tables 2–4 and the associated feature-extracting component type (e.g., model backbone) may be applied to a CSI decoder. In such cases, a receiving network entity (e.g., the network entity 105-b) may indicate which model backbone or hyperparameters are used to derive a reference decoder or derive a relationship between decoder input and output. The transmitting network entity (e.g., the network entity 105-a) may then develop their encoder compatible to the configured decoder structure hyperparameter or feature extracting component type.
[0108] FIG. 6 shows an example of a process flow 600 that supports CSI encoding model structure in accordance with one or more aspects of the present disclosure. The process flow 600 may implement or be implemented by aspects of the wireless communications system 100, the wireless communications system 200, the transformer-based feature-extraction component 300, the MLP mixer-based feature-extraction component 400, the CNN-based feature-extraction component 500, or any combination thereof. For example, the process flow 600 may include a network entity 105-a and a network entity 105-b, which may be examples of corresponding devices as described with reference to FIG. 2. The network entity 105-a, the network entity 105-b, or both may include CSI encoders and decoders, respectively, that may include a feature-extraction component. The feature-extraction component may be an example of any of the feature-extraction components as described with reference to FIGs. 3 through 5.
[0109] Alternative examples of the following may be implemented, where some operations are performed in a different order than described or are not performed at all. In some examples, operations may include additional features not mentioned below, or further operations may be added. Although the network entity 105-a and the network entity 105-b are shown performing the operations of the process flow 600, some aspects of some operations may also be performed by one or more other wireless devices.
[0110] In some examples, prior to obtaining an indication of a feature-extracting component type or one or more hyperparameters, the network entity 105-a may output a capability message indicating a capability of the network entity 105-a to support one or more model structures, the one or more model structures including different combinations of feature-extracting component types and hyperparameters.
[0111] At 605, the network entity 105-b may output, to the network entity 105-a, a first message. For example, the network entity 105-a may obtain, from a network entity 105-b, a first message comprising an indication of a feature-extracting component type for a ML model of a CSI encoder, one or more hyperparameters for the ML model, or both. In some examples, the feature-extracting component type, the one or more hyperparameters, or both may be in accordance with the capability message.
[0112] In some examples, the feature-extracting component type may be a transformer-based feature extracting component type. In such examples, the one or more hyperparameters may include the feature-extracting component, a quantity of modules of the feature-extracting component, a dimension of an input to the feature-extracting component, a dimension of one or more first layers of each first module of multiple first modules of the feature-extracting component, a quantity of calculations in each first module of the multiple first modules, a dimension of multiple calculations in the multiple first modules, a dimension of one or more second layers of each second module of multiple second modules of the feature-extracting component, a quantity of tokens, a compression identifier, or any combination thereof. The transformer-based feature component may be an example of the transformer-based feature-extraction component 300 as described with reference to FIG. 3.
[0113] In some other examples, the feature-extracting component type may be a MLP mixer-based feature extracting component type. In such examples, the one or more hyperparameters may include the feature-extracting component, a quantity of modules of the feature-extracting component, a dimension of an input to the feature-extracting component, a dimension of one or more first layers of each first module of multiple first modules, a dimension of one or more second layers of each second module of multiple second modules, a compression identifier, or any combination thereof. The MLP mixer-based feature component may be an example of the MLP mixer-based feature-extraction component 400 as described with reference to FIG. 4.
[0114] In yet another example, the feature-extracting component type may be a CNN-based feature extracting component type. In such examples, the one or more hyperparameters may include the feature-extracting component, a dimension of an input to the feature-extracting component, a quantity of modules of the feature-extracting component, a kernel size of a first layer at a beginning of the CSI encoder, a stride of the first layer at the beginning of the CSI encoder, a quantity of layers within each of multiple modules, a dimension of an output within the multiple modules, a kernel size of the quantity of layers of each of the multiple modules, a stride of the quantity of layers of each of the multiple modules, or any combination thereof. The CNN-based feature component may be an example of the CNN-based feature-extraction component 500 as described with reference to FIG. 5.
[0115] In some examples, the first message may include one or more model parameters. For example, same signaling may be used for sharing model parameters and hyperparameters. In such examples, the first message may include a first part or portion that is used to indicate (e.g., convey) the feature-extracting component type, the one or more hyperparameters, or both. Additionally, the first message may include a second part or portion that is used to indicate (e.g., convey) the one or more model parameters.
[0116] The one or more hyperparameters may be external to the ML model, and values of the one or more hyperparameters may be set prior to training the ML model. For example, the hyperparameters may not be training weights.
[0117] In some examples, the first message may indicate the one or more hyperparameters are separately (e.g., one-by-one) or as a combination. For example, the combination may be one of multiple predefined combinations of hyperparameters (e.g., associated with a feature-extracting component type) .
[0118] At 610, the network entity 105-a may encode CSI. For example, the network entity 105-a may encode CSI via a CSI encoder, where the CSI encoder is based on the one or more hyperparameters, comprises a feature-extracting component of the indicated feature-extracting component type, or both. In examples in which the first message includes the one or more model parameters, encoding the CSI may be based on the one or more model parameters.
[0119] In some examples, the feature-extracting component type, the one or more hyperparameters, or both may be applied directly to the CSI encoder that is used to encode the CSI. Alternatively, the feature-extracting component type, the one or more hyperparameters, or both may be applied indirectly to the CSI encoder. That is, the network entity 105-a may obtain, via the first message, the feature-extracting component type, the one or more hyperparameters, or both that are indicative of a mapping between an input to the CSI encoder and an output of the CSI encoder. The network entity 105-a may train the ML model of the CSI encoder using the mapping, where encoding the CSI is based on the trained model.
[0120] At 615, the network entity 105-a may output a second message. For example, the network entity 105-a may output, to the network entity 105-b, the second message that is obtained via the CSI encoder at the network entity 105-a. In some examples, the second message may be a latent message.
[0121] At 620, the network entity 105-b may decode the second message. For example, the network entity 105-b may decode the second message to obtain the CSI. The network entity 105-b may decode the second message using a CSI decoder that includes a ML model. The CSI decoder may be based on the one or more hyperparameters, include the feature-extracting component of the indicated feature-extracting component type, or both. That is, the CSI decoder may include same components or apply same parameters as the CSI encoder at the network entity 105-a but in a reverse order.
[0122] FIG. 7 shows a block diagram 700 of a device 705 that supports CSI encoding model structure 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) .
[0123] 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.
[0124] 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.
[0125] 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 CSI encoding model structure 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.
[0126] 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) .
[0127] 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) .
[0128] 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.
[0129] 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 obtaining, from a second network entity, a first message including an indication of a feature-extracting component type for a ML model of a CSI encoder, one or more hyperparameters for the ML model, or both. The communications manager 720 is capable of, configured to, or operable to support a means for encoding CSI via the CSI encoder, where the CSI encoder is based on the one or more hyperparameters, includes a feature-extracting component of the indicated feature-extracting component type, or both. The communications manager 720 is capable of, configured to, or operable to support a means for outputting, to the second network entity, a second message that is obtained via the CSI encoder at the first network entity.
[0130] 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 improved coordination between devices and improved performance related to encoding CSI.
[0131] FIG. 8 shows a block diagram 800 of a device 805 that supports CSI encoding model structure 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) .
[0132] 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.
[0133] 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.
[0134] The device 805, or various components thereof, may be an example of means for performing various aspects of CSI encoding model structure as described herein. For example, the communications manager 820 may include an encoding model information component 825, an encoding component 830, a CSI 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.
[0135] The communications manager 820 may support wireless communications in accordance with examples as disclosed herein. The encoding model information component 825 is capable of, configured to, or operable to support a means for obtaining, from a second network entity, a first message including an indication of a feature-extracting component type for a ML model of a CSI encoder, one or more hyperparameters for the ML model, or both. The encoding component 830 is capable of, configured to, or operable to support a means for encoding CSI via the CSI encoder, where the CSI encoder is based on the one or more hyperparameters, includes a feature-extracting component of the indicated feature-extracting component type, or both. The CSI component 835 is capable of, configured to, or operable to support a means for outputting, to the second network entity, a second message that is obtained via the CSI encoder at the first network entity.
[0136] FIG. 9 shows a block diagram 900 of a communications manager 920 that supports CSI encoding model structure 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 CSI encoding model structure as described herein. For example, the communications manager 920 may include an encoding model information component 925, an encoding component 930, a CSI component 935, a capability component 940, a training component 945, 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) . The communications may include communications within a protocol layer of a protocol stack, communications associated with a logical channel of a protocol stack (e.g., between protocol layers of a protocol stack, within a device, component, or virtualized component associated with a network entity 105, between devices, components, or virtualized components associated with a network entity 105) , or any combination thereof.
[0137] The communications manager 920 may support wireless communications in accordance with examples as disclosed herein. The encoding model information component 925 is capable of, configured to, or operable to support a means for obtaining, from a second network entity, a first message including an indication of a feature-extracting component type for a ML model of a CSI encoder, one or more hyperparameters for the ML model, or both. The encoding component 930 is capable of, configured to, or operable to support a means for encoding CSI via the CSI encoder, where the CSI encoder is based on the one or more hyperparameters, includes a feature-extracting component of the indicated feature-extracting component type, or both. The CSI component 935 is capable of, configured to, or operable to support a means for outputting, to the second network entity, a second message that is obtained via the CSI encoder at the first network entity.
[0138] In some examples, the feature-extracting component type includes a transformer-based feature extracting component type. In such examples, the one or more hyperparameters include the feature-extracting component, a quantity of modules of the feature-extracting component, a dimension of an input to the feature-extracting component, a dimension of one or more first layers of each first module of a set of multiple first modules of the feature-extracting component, a quantity of calculations in each first module of the set of multiple first modules, a dimension of a set of multiple calculations in the set of multiple first modules, a dimension of one or more second layers of each second module of a set of multiple second modules of the feature-extracting component, a quantity of tokens, a compression identifier, or any combination thereof.
[0139] In some examples, the feature-extracting component type includes a MLP mixer-based feature extracting component type. In such examples, the one or more hyperparameters include the feature-extracting component, a quantity of modules of the feature-extracting component, a dimension of an input to the feature-extracting component, a dimension of one or more first layers of each first module of a set of multiple first modules, a dimension of one or more second layers of each second module of a set of multiple second modules, a compression identifier, or any combination thereof.
[0140] In some examples, the feature-extracting component type includes a CNN-based feature extracting component type. In such examples, the one or more hyperparameters include the feature-extracting component, a dimension of an input to the feature-extracting component, a quantity of modules of the feature-extracting component, a kernel size of a first layer at a beginning of the CSI encoder, a stride of the first layer at the beginning of the CSI encoder, a quantity of layers within each of a set of multiple modules, a dimension of an output within the set of multiple modules, a kernel size of the quantity of layers of each of the set of multiple modules, a stride of the quantity of layers of each of the set of multiple modules, or any combination thereof.
[0141] In some examples, the capability component 940 is capable of, configured to, or operable to support a means for outputting, prior to obtaining the indication of the feature-extracting component type and the one or more hyperparameters, a capability message indicating a capability of the first network entity to support one or more model structures, the one or more model structures including different combinations of feature-extracting component types and hyperparameters, where the feature-extracting component type and the one or more hyperparameters are in accordance with the capability message.
[0142] In some examples, the first message further includes one or more model parameters. In some examples, encoding the CSI is based on the one or more model parameters.
[0143] In some examples, the one or more hyperparameters are external to the ML model and values of the one or more hyperparameters are set prior to training the ML model.
[0144] In some examples, the one or more hyperparameters are indicated separately.
[0145] In some examples, the one or more hyperparameters are indicated as a combination, the combination being one of a set of multiple combinations of predefined hyperparameters.
[0146] In some examples, the second message includes a latent message.
[0147] In some examples, the feature-extracting component type, the one or more hyperparameters, or both are applied directly to the CSI encoder that is used to encode the CSI.
[0148] In some examples, the encoding model information component 925 is capable of, configured to, or operable to support a means for obtaining, via the first message, the feature-extracting component type, the one or more hyperparameters, or both that are indicative of a mapping between an input to the CSI encoder and an output of the CSI encoder. In some examples, the training component 945 is capable of, configured to, or operable to support a means for training the ML model of the CSI encoder using the mapping, where encoding the CSI is based on the trained model.
[0149] FIG. 10 shows a diagram of a system 1000 including a device 1005 that supports CSI encoding model structure 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 communicate with other network devices or network equipment such as one or more of the network entities 105, UEs 115, or any combination thereof. The communications may include communications over one or more wired interfaces, over one or more wireless interfaces, or any combination thereof. The device 1005 may include components that support outputting and obtaining 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) .
[0150] 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) .
[0151] 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) .
[0152] 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 CSI encoding model structure) . 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) .
[0153] 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.
[0154] 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) .
[0155] 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.
[0156] 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 obtaining, from a second network entity, a first message including an indication of a feature-extracting component type for a ML model of a CSI encoder, one or more hyperparameters for the ML model, or both. The communications manager 1020 is capable of, configured to, or operable to support a means for encoding CSI via the CSI encoder, where the CSI encoder is based on the one or more hyperparameters, includes a feature-extracting component of the indicated feature-extracting component type, or both. The communications manager 1020 is capable of, configured to, or operable to support a means for outputting, to the second network entity, a second message that is obtained via the CSI encoder at the first network entity.
[0157] By including or configuring the communications manager 1020 in accordance with examples as described herein, the device 1005 may support techniques for improved coordination between devices.
[0158] 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 CSI encoding model structure 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.
[0159] FIG. 11 shows a flowchart illustrating a method 1100 that supports CSI encoding model structure in accordance with one or more aspects of the present disclosure. The operations of the method 1100 may be implemented by a network entity or its components as described herein. For example, the operations of the method 1100 may be performed by a network entity as described with reference to FIGs. 1 through 10. In some examples, a network entity may execute a set of instructions to control the functional elements of the network entity to perform the described functions. Additionally, or alternatively, the network entity may perform aspects of the described functions using special-purpose hardware.
[0160] At 1105, the method may include obtaining, from a second network entity, a first message including an indication of a feature-extracting component type for a ML model of a CSI encoder, one or more hyperparameters for the ML model, or both. The operations of 1105 may be performed in accordance with examples as disclosed herein. In some examples, aspects of the operations of 1105 may be performed by an encoding model information component 925 as described with reference to FIG. 9.
[0161] At 1110, the method may include encoding CSI via the CSI encoder, where the CSI encoder is based on the one or more hyperparameters, includes a feature-extracting component of the indicated feature-extracting component type, or both. The operations of 1110 may be performed in accordance with examples as disclosed herein. In some examples, aspects of the operations of 1110 may be performed by an encoding component 930 as described with reference to FIG. 9.
[0162] At 1115, the method may include outputting, to the second network entity, a second message that is obtained via the CSI encoder at the first network entity. The operations of 1115 may be performed in accordance with examples as disclosed herein. In some examples, aspects of the operations of 1115 may be performed by a CSI component 935 as described with reference to FIG. 9.
[0163] FIG. 12 shows a flowchart illustrating a method 1200 that supports CSI encoding model structure in accordance with one or more aspects of the present disclosure. The operations of the method 1200 may be implemented by a network entity or its components as described herein. For example, the operations of the method 1200 may be performed by a network entity as described with reference to FIGs. 1 through 10.In some examples, a network entity may execute a set of instructions to control the functional elements of the network entity to perform the described functions. Additionally, or alternatively, the network entity may perform aspects of the described functions using special-purpose hardware.
[0164] At 1205, the method may include outputting, prior to obtaining an indication of a feature-extracting component type, one or more hyperparameters, or both, a capability message indicating a capability of the first network entity to support one or more model structures, the one or more model structures including different combinations of feature-extracting component types and hyperparameters. The operations of 1205 may be performed in accordance with examples as disclosed herein. In some examples, aspects of the operations of 1205 may be performed by a capability component 940 as described with reference to FIG. 9.
[0165] At 1210, the method may include obtaining, from a second network entity, a first message including the indication of the feature-extracting component type for a ML model of a CSI encoder, the one or more hyperparameters for the ML model, or both, where the feature-extracting component type and the one or more hyperparameters are in accordance with the capability message. The operations of 1210 may be performed in accordance with examples as disclosed herein. In some examples, aspects of the operations of 1210 may be performed by an encoding model information component 925 as described with reference to FIG. 9.
[0166] At 1215, the method may include encoding CSI via the CSI encoder, where the CSI encoder is based on the one or more hyperparameters, includes a feature-extracting component of the indicated feature-extracting component type, or both. The operations of 1215 may be performed in accordance with examples as disclosed herein. In some examples, aspects of the operations of 1215 may be performed by an encoding component 930 as described with reference to FIG. 9.
[0167] At 1220, the method may include outputting, to the second network entity, a second message that is obtained via the CSI encoder at the first network entity. The operations of 1220 may be performed in accordance with examples as disclosed herein. In some examples, aspects of the operations of 1220 may be performed by a CSI component 935 as described with reference to FIG. 9.
[0168] The following provides an overview of aspects of the present disclosure:
[0169] Aspect 1: A method for wireless communications by a first network entity, comprising: obtaining, from a second network entity, a first message comprising an indication of a feature-extracting component type for a machine learning model of a CSI encoder, one or more hyperparameters for the machine learning model, or both; encoding CSI via the CSI encoder, wherein the CSI encoder is based at least in part on the one or more hyperparameters, comprises a feature-extracting component of the indicated feature-extracting component type, or both; and outputting, to the second network entity, a second message that is obtained via the CSI encoder at the first network entity.
[0170] Aspect 2: The method of aspect 1, wherein the feature-extracting component type comprises a transformer-based feature extracting component type, and wherein: the one or more hyperparameters comprise the feature-extracting component, a quantity of modules of the feature-extracting component, a dimension of an input to the feature-extracting component, a dimension of one or more first layers of each first module of a plurality of first modules of the feature-extracting component, a quantity of calculations in each first module of the plurality of first modules, a dimension of a plurality of calculations in the plurality of first modules, a dimension of one or more second layers of each second module of a plurality of second modules of the feature-extracting component, a quantity of tokens, a compression identifier, or any combination thereof.
[0171] Aspect 3: The method of any of aspects 1 through 2, wherein the feature-extracting component type comprises a MLP mixer-based feature extracting component type, and wherein: the one or more hyperparameters comprise the feature-extracting component, a quantity of modules of the feature-extracting component, a dimension of an input to the feature-extracting component, a dimension of one or more first layers of each first module of a plurality of first modules, a dimension of one or more second layers of each second module of a plurality of second modules, a compression identifier, or any combination thereof.
[0172] Aspect 4: The method of any of aspects 1 through 3, wherein the feature-extracting component type comprises a CNN-based feature extracting component type, and wherein: the one or more hyperparameters comprise the feature-extracting component, a dimension of an input to the feature-extracting component, a quantity of modules of the feature-extracting component, a kernel size of a first layer at a beginning of the CSI encoder, a stride of the first layer at the beginning of the CSI encoder, a quantity of layers within each of a plurality of modules, a dimension of an output within the plurality of modules, a kernel size of the quantity of layers of each of the plurality of modules, a stride of the quantity of layers of each of the plurality of modules, or any combination thereof.
[0173] Aspect 5: The method of any of aspects 1 through 4, further comprising: outputting, prior to obtaining the indication of the feature-extracting component type and the one or more hyperparameters, a capability message indicating a capability of the first network entity to support one or more model structures, the one or more model structures comprising different combinations of feature-extracting component types and hyperparameters, wherein the feature-extracting component type and the one or more hyperparameters are in accordance with the capability message.
[0174] Aspect 6: The method of any of aspects 1 through 5, wherein the first message further comprises one or more model parameters, and encoding the CSI is based at least in part on the one or more model parameters.
[0175] Aspect 7: The method of any of aspects 1 through 6, wherein the one or more hyperparameters are external to the machine learning model and values of the one or more hyperparameters are set prior to training the machine learning model.
[0176] Aspect 8: The method of any of aspects 1 through 7, wherein the one or more hyperparameters are indicated separately.
[0177] Aspect 9: The method of any of aspects 1 through 8, wherein the one or more hyperparameters are indicated as a combination, the combination being one of a plurality of combinations of predefined hyperparameters.
[0178] Aspect 10: The method of any of aspects 1 through 9, wherein the second message comprises a latent message.
[0179] Aspect 11: The method of any of aspects 1 through 10, wherein the feature-extracting component type, the one or more hyperparameters, or both are applied directly to the CSI encoder that is used to encode the CSI.
[0180] Aspect 12: The method of any of aspects 1 through 11, further comprising: obtaining, via the first message, the feature-extracting component type, the one or more hyperparameters, or both that are indicative of a mapping between an input to the CSI encoder and an output of the CSI encoder; training the machine learning model of the CSI encoder using the mapping, wherein encoding the CSI is based at least in part on the trained model.
[0181] Aspect 13: 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 12.
[0182] Aspect 14: A first network entity for wireless communications, comprising at least one means for performing a method of any of aspects 1 through 12.
[0183] Aspect 15: 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 12.
[0184] 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.
[0185] 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.
[0186] 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.
[0187] 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.
[0188] 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.
[0189] 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.
[0190] 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. ”
[0191] 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. ”
[0192] 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.
[0193] 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.
[0194] 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.
[0195] 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:obtain, from a second network entity, a first message comprising an indication of a feature-extracting component type for a machine learning model of a channel state information (CSI) encoder, one or more hyperparameters for the machine learning model, or both;encode CSI via the CSI encoder, wherein the CSI encoder is based at least in part on the one or more hyperparameters, comprises a feature-extracting component of the indicated feature-extracting component type, or both; andoutput, to the second network entity, a second message that is obtained via the CSI encoder at the first network entity.2.The first network entity of claim 1, wherein the feature-extracting component type comprises a transformer-based feature extracting component type, and wherein:the one or more hyperparameters comprise the feature-extracting component, a quantity of modules of the feature-extracting component, a dimension of an input to the feature-extracting component, a dimension of one or more first layers of each first module of a plurality of first modules of the feature-extracting component, a quantity of calculations in each first module of the plurality of first modules, a dimension of a plurality of calculations in the plurality of first modules, a dimension of one or more second layers of each second module of a plurality of second modules of the feature-extracting component, a quantity of tokens, a compression identifier, or any combination thereof.3.The first network entity of claim 1, wherein the feature-extracting component type comprises a multilayer perceptron (MLP) mixer-based feature extracting component type, and wherein:the one or more hyperparameters comprise the feature-extracting component, a quantity of modules of the feature-extracting component, a dimension of an input to the feature-extracting component, a dimension of one or more first layers of each first module of a plurality of first modules, a dimension of one or more second layers of each second module of a plurality of second modules, a compression identifier, or any combination thereof.4.The first network entity of claim 1, wherein the feature-extracting component type comprises a convolutional neural network (CNN) -based feature extracting component type, and wherein:the one or more hyperparameters comprise the feature-extracting component, a dimension of an input to the feature-extracting component, a quantity of modules of the feature-extracting component, a kernel size of a first layer at a beginning of the CSI encoder, a stride of the first layer at the beginning of the CSI encoder, a quantity of layers within each of a plurality of modules, a dimension of an output within the plurality of modules, a kernel size of the quantity of layers of each of the plurality of modules, a stride of the quantity of layers of each of the plurality of modules, or any combination thereof.5.The first network entity of claim 1, wherein the one or more processors are individually or collectively further operable to execute the code to cause the first network entity to:output, prior to obtaining the indication of the feature-extracting component type and the one or more hyperparameters, a capability message indicating a capability of the first network entity to support one or more model structures, the one or more model structures comprising different combinations of feature-extracting component types and hyperparameters, wherein the feature-extracting component type and the one or more hyperparameters are in accordance with the capability message.6.The first network entity of claim 1, wherein:the first message further comprises one or more model parameters, andencoding the CSI is based at least in part on the one or more model parameters.7.The first network entity of claim 1, wherein the one or more hyperparameters are external to the machine learning model and values of the one or more hyperparameters are set prior to training the machine learning model.8.The first network entity of claim 1, wherein:the one or more hyperparameters are indicated separately.9.The first network entity of claim 1, wherein the one or more hyperparameters are indicated as a combination, the combination being one of a plurality of combinations of predefined hyperparameters.10.The first network entity of claim 1, wherein the second message comprises a latent message.11.The first network entity of claim 1, wherein the feature-extracting component type, the one or more hyperparameters, or both are applied directly to the CSI encoder that is used to encode the CSI.12.The first network entity of claim 1, wherein the one or more processors are individually or collectively further operable to execute the code to cause the first network entity to:obtain, via the first message, the feature-extracting component type, the one or more hyperparameters, or both that are indicative of a mapping between an input to the CSI encoder and an output of the CSI encoder; andtrain the machine learning model of the CSI encoder using the mapping, wherein encoding the CSI is based at least in part on the trained model.13.A method for wireless communications by a first network entity, comprising:obtaining, from a second network entity, a first message comprising an indication of a feature-extracting component type for a machine learning model of a channel state information (CSI) encoder, one or more hyperparameters for the machine learning model, or both;encoding CSI via the CSI encoder, wherein the CSI encoder is based at least in part on the one or more hyperparameters, comprises a feature-extracting component of the indicated feature-extracting component type, or both; andoutputting, to the second network entity, a second message that is obtained via the CSI encoder at the first network entity.14.The method of claim 13, wherein the feature-extracting component type comprises a transformer-based feature extracting component type, and wherein:the one or more hyperparameters comprise the feature-extracting component, a quantity of modules of the feature-extracting component, a dimension of an input to the feature-extracting component, a dimension of one or more first layers of each first module of a plurality of first modules of the feature-extracting component, a quantity of calculations in each first module of the plurality of first modules, a dimension of a plurality of calculations in the plurality of first modules, a dimension of one or more second layers of each second module of a plurality of second modules of the feature-extracting component, a quantity of tokens, a compression identifier, or any combination thereof.15.The method of claim 13, wherein the feature-extracting component type comprises a multilayer perceptron (MLP) mixer-based feature extracting component type, and wherein:the one or more hyperparameters comprise the feature-extracting component, a quantity of modules of the feature-extracting component, a dimension of an input to the feature-extracting component, a dimension of one or more first layers of each first module of a plurality of first modules, a dimension of one or more second layers of each second module of a plurality of second modules, a compression identifier, or any combination thereof.16.The method of claim 13, wherein the feature-extracting component type comprises a convolutional neural network (CNN) -based feature extracting component type, and wherein:the one or more hyperparameters comprise the feature-extracting component, a dimension of an input to the feature-extracting component, a quantity of modules of the feature-extracting component, a kernel size of a first layer at a beginning of the CSI encoder, a stride of the first layer at the beginning of the CSI encoder, a quantity of layers within each of a plurality of modules, a dimension of an output within the plurality of modules, a kernel size of the quantity of layers of each of the plurality of modules, a stride of the quantity of layers of each of the plurality of modules, or any combination thereof.17.The method of claim 13, further comprising:outputting, prior to obtaining the indication of the feature-extracting component type and the one or more hyperparameters, a capability message indicating a capability of the first network entity to support one or more model structures, the one or more model structures comprising different combinations of feature-extracting component types and hyperparameters, wherein the feature-extracting component type and the one or more hyperparameters are in accordance with the capability message.18.The method of claim 13, wherein:the first message further comprises one or more model parameters, andencoding the CSI is based at least in part on the one or more model parameters.19.The method of claim 13, wherein the one or more hyperparameters are external to the machine learning model and values of the one or more hyperparameters are set prior to training the machine learning model.20.A non-transitory computer-readable medium storing code for wireless communications, the code comprising instructions executable by one or more processors to:obtain, from a second network entity, a first message comprising an indication of a feature-extracting component type for a machine learning model of a channel state information (CSI) encoder, one or more hyperparameters for the machine learning model, or both;encode CSI via the CSI encoder, wherein the CSI encoder is based at least in part on the one or more hyperparameters, comprises a feature-extracting component of the indicated feature-extracting component type, or both; andoutput, to the second network entity, a second message that is obtained via the CSI encoder at the first network entity.