Method for determining zone membership in zone-based joint learning

Abstract

A processor-implemented method includes receiving, by a user equipment (UE), a zone determination function based on a joint learning process registered for training a first joint learning model. The method also includes determining, by the UE, a zone membership according to UE parameters and the zone determination function. The method also includes selecting, by the UE, the first joint learning model based on the zone membership. The method includes training, by the UE, the first joint learning model.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to U.S. patent application No. 18 / 102,601, filed on January 27, 2023, entitled “METHOD OF DETERMINING ZONE MEMBERSHIP IN ZONE-BASED FEDERATED LEARNING,” which claims the benefit of U.S. Provisional Patent Application No. 63 / 346,252, filed on May 26, 2022, entitled “METHOD OF DETERMINING ZONE MEMBERSHIP IN ZONE-BASED FEDERATED LEARNING,” the disclosures of which are expressly incorporated herein by reference in their entireties. Technical Field

[0003] The present disclosure relates generally to wireless communications, and more particularly to methods of determining zone membership in zone-based federated learning. Background Art

[0004] Wireless communication systems are widely deployed to provide various telecommunication services such as telephone, video, data, messaging, and broadcasting. Typical wireless communication systems may employ multiple access technologies that can support communication with multiple users by sharing available system resources (e.g., bandwidth, transmit power, etc.). Examples of such multiple access technologies include code division multiple access (CDMA) systems, time division multiple access (TDMA) systems, frequency division multiple access (FDMA) systems, orthogonal frequency division multiple access (OFDMA) systems, single carrier frequency division multiple access (SC-FDMA) systems, time division synchronous code division multiple access (TD-SCDMA) systems, and long term evolution (LTE). LTE / LTE Advanced is a set of enhancements to the Universal Mobile Telecommunications System (UMTS) mobile standard issued by the Third Generation Partnership Project (3GPP). Narrowband (NB) Internet of Things (IoT) and enhanced machine type communication (eMTC) are sets of enhancements to LTE for machine type communication.

[0005] A wireless communication network may include multiple base stations (BSs) that may support communications for multiple user equipments (UEs). User equipments (UEs) may communicate with base stations (BSs) via downlinks and uplinks. Downlinks (or forward links) refer to the communication link from a BS to a UE, while uplinks (or reverse links) refer to the communication link from a UE to a BS. As will be described in more detail, a BS may be referred to as a Node B, an evolved Node B (eNB), a gNB, an access point (AP), a radio head, a transmit and receive point (TRP), a new radio (NR) BS, a 5G Node B, etc.

[0006] The above multiple access technologies have been adopted in various telecommunication standards to provide a common protocol that enables different user equipment to communicate at city, country, region, and even global levels. New Radio (NR) (also referred to as 5G) is a set of enhancements to the LTE mobile standard released by the Third Generation Partnership Project (3GPP). NR is designed to better integrate with other open standards by improving spectrum efficiency, reducing costs, improving services, utilizing new spectrum, and using orthogonal frequency division multiplexing (OFDM) (CP-OFDM) with cyclic prefix (CP) on the downlink (DL), using CP-OFDM and / or SC-FDM (e.g., also known as discrete Fourier transform spread OFDM (DFT-s-OFDM)) on the uplink (UL), and supporting beamforming, multiple-input multiple-output (MIMO) antenna technology, and carrier aggregation, so as to better support mobile broadband Internet access.

[0007] An artificial neural network may include an interconnected group of artificial neurons (e.g., a neuron model). An artificial neural network may be a computing device or represented as a method performed by a computing device. A convolutional neural network (such as a deep convolutional neural network) is a type of feedforward artificial neural network. A convolutional neural network may include layers of neurons that may be configured in a tiled receptive field. It would be desirable to apply neural network processing to wireless communications to achieve greater efficiency. Summary of the invention

[0008] In various aspects of the present disclosure, a processor-implemented method includes receiving, by a user equipment (UE), a zone determination function based on registering a federated learning process for training a first federated learning model. The method also includes determining, by the UE, zone membership based on UE parameters and the zone determination function. The method also includes selecting, by the UE, the first federated learning model based on the zone membership. The method includes training the first federated learning model by the UE.

[0009] Other aspects of the present disclosure relate to an apparatus. The apparatus has a memory and one or more processors coupled to the memory. The processor is configured to receive a zone determination function based on registering a joint learning process for training a first joint learning model. The processor is also configured to determine zone membership based on UE parameters and the zone determination function. The processor is also configured to select the first joint learning model based on the zone membership. The processor is configured to train the first joint learning model.

[0010] Other aspects of the present disclosure relate to an apparatus. The apparatus includes a component for receiving, by a user equipment (UE), a zone determination function based on registering a federated learning process for training a first federated learning model. The apparatus also includes a component for determining, by the UE, zone membership based on UE parameters and the zone determination function. The apparatus also includes a component for selecting, by the UE, a first federated learning model based on the zone membership. The apparatus includes a component for training the first federated learning model by the UE.

[0011] In yet other aspects of the present disclosure, a non-transitory computer-readable medium having program code recorded thereon is disclosed. The program code is executed by a processor and includes program code for receiving a zone determination function by a user equipment (UE) based on a joint learning process registered for training a first joint learning model. The program code also includes program code for determining zone membership by the UE based on UE parameters and the zone determination function. The program code also includes program code for selecting a first joint learning model by the UE based on zone membership. The program code also includes program code for training the first joint learning model by the UE.

[0012] Aspects generally include methods, apparatus, systems, computer program products, non-transitory computer readable media, user equipment, base stations, wireless communication devices, and processing systems as substantially described with reference to and as illustrated in the accompanying drawings and description.

[0013] The features and technical advantages of examples according to the present disclosure have been outlined quite broadly above so that the following specific embodiments may be better understood. Additional features and advantages will be described. The disclosed concepts and specific examples may be easily used as a basis for modifying or designing other structures for achieving the same purpose of the present disclosure. Such equivalent constructions do not depart from the scope of the appended claims. The characteristics of the disclosed concepts, both in terms of their organization and method of operation, and the associated advantages will be better understood by considering the following description in conjunction with the accompanying drawings. Each of the figures in the accompanying drawings is provided for the purpose of illustration and description and not as a definition of limitations to the claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order that the features of the present disclosure may be understood in detail, a more specific description may be made with reference to various aspects, some of which are illustrated in the accompanying drawings. It should be noted, however, that the accompanying drawings illustrate only certain aspects of the present disclosure and therefore should not be considered as limiting the scope thereof, as the description may allow for other equivalent aspects. The same reference numerals in different drawings may identify the same or similar elements.

[0015] Figure 1 is a block diagram conceptually illustrating an example of a wireless communication network in accordance with various aspects of the present disclosure.

[0016] Figure 2 is a block diagram conceptually illustrating an example of a base station communicating with a user equipment (UE) in a wireless communication network according to various aspects of the present disclosure.

[0017] Figure 3 is a block diagram illustrating an example decomposed base station architecture in accordance with aspects of the present disclosure.

[0018] Figure 4 An example implementation of designing a neural network using a system on a chip (SOC) including a general-purpose processor in accordance with certain aspects of the present disclosure is illustrated.

[0019] Figure 5A , Figure 5B and Figure 5C is a diagram illustrating a neural network according to aspects of the present disclosure.

[0020] Figure 5D is a diagram illustrating an exemplary deep convolutional network (DCN) according to aspects of the present disclosure.

[0021] Figure 6 is a block diagram illustrating an exemplary deep convolutional network (DCN) according to aspects of the present disclosure.

[0022] Figure 7 is a diagram illustrating an example zone network topology for zone-based federated learning in accordance with aspects of the present disclosure.

[0023] Figure 8 is a block diagram illustrating an example of participating devices including a federated learning (FL) manager according to aspects of the present disclosure.

[0024] Fig. 9 is a timeline illustrating a zone membership check in accordance with aspects of the present disclosure.

[0025] Fig.10 is a flow chart illustrating an example process for determining zone membership in zone-based federated learning according to aspects of the present disclosure. DETAILED DESCRIPTION

[0026] The following is a more comprehensive description of various aspects of the present disclosure with reference to the accompanying drawings. However, the present disclosure can be embodied in many different forms and should not be construed as being limited to any specific structure or function presented throughout the present disclosure. Instead, these aspects are provided so that the present disclosure will be thorough and complete, and the scope of protection of the present disclosure will be fully conveyed to those skilled in the art. Based on the teachings, those skilled in the art should recognize that the scope of the present disclosure is intended to cover any aspect of the present disclosure, whether the aspect is implemented independently of any other aspect of the present disclosure or implemented in combination with any other aspect. For example, a device may be implemented or a method may be practiced using any number of aspects described. In addition, the scope of the present disclosure is intended to cover such devices or methods practiced using other structures, functionality, or structures and functionality as supplements to the various aspects of the present disclosure described or in addition. It should be understood that any aspect of the present disclosure disclosed may be embodied by one or more elements of the claims.

[0027] Several aspects of telecommunication systems will now be presented with reference to various devices and techniques. These devices and techniques will be described in the following detailed description and illustrated in the accompanying drawings by various blocks, modules, components, circuits, steps, processes, algorithms, etc. (collectively referred to as "elements"). These elements can be implemented using hardware, software, or a combination thereof. Whether these elements are implemented as hardware or software depends on the specific application and the design constraints imposed on the overall system.

[0028] It should be noted that although various aspects may be described using terms commonly associated with 5G and later wireless technologies, various aspects of the present disclosure may be applied in communication systems based on other generations (such as and including 3G and / or 4G technologies).

[0029] Federated learning is a machine learning technique that trains a federated learning model across multiple decentralized edge devices or servers that maintain local data samples without sharing the data samples with the server. Federated learning provides the benefits of privacy-preserving machine learning and continuous learning on the edge. However, when the data at the device is non-independent and identically distributed (non-IID), the performance of federated learning is impaired. Data augmentation is a method to address non-IID data. Another method is zone-based federated learning. Zone-based federated learning groups participating devices into zones that contribute to the distribution of non-IID data at the edge. Aspects of the present disclosure include a method for determining zone membership of devices participating in a federated learning process for training a federated learning model.

[0030] According to aspects of the present disclosure, when a device registers to participate in federated learning, the device is provided with an up-to-date zone topology map and a "zone determination function". This function accepts a set of parameters from the device and returns the zone information to which the device belongs. These parameters may include, for example, global positioning system (GPS) coordinates, or user purchase transaction history. If zone membership is determined locally, the parameters (e.g., user purchase transaction history) do not leave the device.

[0031] In some aspects, a device periodically checks its zone membership and tabulates its training data based on the zone membership. When a device is ready to perform local training, the device communicates with the federated learning zone manager of the zone to which the device belongs. Whenever the zone topology or zone determination function changes, the zone partitioning keeper updates and notifies all participating devices.

[0032] In other aspects, the device stores the training data along with parameters used by the zone membership function. For example, if attempting to use sensor data to train a human activity recognition (HAR) model, and if the zone partitioning holder provides a zone determination function that accepts GPS coordinates as parameters, the device can store the raw sensor data along with the GPS information in a sequential or time-stamped manner. When the device is ready to perform local training, the device can use the GPS data included in the data sample to determine which zone the data will be used for.

[0033] Zone membership checks may be performed periodically or in an event-driven manner. According to aspects of the present disclosure, the device stores locally generated training, testing, and validation data to reflect the zone in which the data was collected. The zone determination functionality may be used in an offline mode (e.g., not connected to a network). According to aspects of the present disclosure, the device maintains storage even when not connected to a network (e.g., moving from zone 1 to zone 2). When connectivity is restored, previously stored training weights may be uploaded to the zone 1 manager even when the device has moved to a different zone (e.g., zone 2).

[0034] Figure 11 is a diagram illustrating a network 100 in which various aspects of the present disclosure may be practiced. The network 100 may be a 5G or NR network, or some other wireless network (such as an LTE network). The wireless network 100 may include a plurality of BSs 110 (shown as BSs 110a, BSs 110b, BSs 110c, and BSs 110d) and other network entities. A BS is an entity that communicates with a user equipment (UE), and may also be referred to as a base station, an NR BS, a Node B, a gNB, a 5G Node B, an access point, a transmission and reception point (TRP), a network node, a network entity, etc. The BS may be implemented as an aggregated base station, a decomposed base station, an integrated access and backhaul (IAB) node, a relay node, a side link node, etc. The BS may be implemented in an aggregated or monolithic base station architecture, or alternatively in a decomposed base station architecture, and may include one or more of a central unit (CU), a distributed unit (DU), a radio unit (RU), a near real-time (near RT) RAN intelligent controller (RIC), or a non-real-time (non-RT) RIC. Each BS can provide communication coverage for a specific geographical area. In 3GPP, the term "cell" can refer to the coverage area of ​​a BS and / or a BS subsystem serving the coverage area, depending on the context in which the term is used.

[0035] A BS may provide communication coverage for a macro cell, a pico cell, a femto cell, and / or another type of cell. A macro cell may cover a relatively large geographic area (e.g., a radius of several kilometers) and may allow unrestricted access by UEs with service subscriptions. A pico cell may cover a relatively small geographic area and may allow unrestricted access by UEs with service subscriptions. A femto cell may cover a relatively small geographic area (e.g., a home) and may allow restricted access by UEs associated with the femto cell (e.g., UEs in a closed subscriber group (CSG)). A BS for a macro cell may be referred to as a macro BS. A BS for a pico cell may be referred to as a pico BS. A BS for a femto cell may be referred to as a femto BS or a home BS. In Figure 1 In the example shown in , BS 110a may be a macro BS for macro cell 102a, BS 110b may be a pico BS for pico cell 102b, and BS 110c may be a femto BS for femto cell 102c. A BS may support one or more (e.g., three) cells. The terms "eNB", "base station", "NR BS", "gNB", "AP", "Node B", "5G NB", "TRP", and "cell" may be used interchangeably.

[0036] In some aspects, the cell need not be stationary, and the geographic area of ​​the cell may move depending on the location of the mobile BS. In some aspects, the BSs may be interconnected with each other and / or to one or more other BSs or network nodes (not shown) in the wireless network 100 through various types of backhaul interfaces (such as direct physical connections, virtual networks, etc.) using any suitable transport network.

[0037] The wireless network 100 may also include a relay station. A relay station is an entity that can receive transmissions of data from an upstream station (e.g., a BS or a UE) and transmit the transmissions of the data to a downstream station (e.g., a UE or a BS). A relay station may also be a UE that can relay transmissions for other UEs. Figure 1 In the example shown in FIG. 1 , a relay station 110 d may communicate with a macro BS 110 a and a UE 120 d to facilitate communication between the BS 110 a and the UE 120 d. A relay station may also be referred to as a relay BS, a relay base station, a relay, or the like.

[0038] The wireless network 100 may be a heterogeneous network including different types of BSs (e.g., macro BSs, pico BSs, femto BSs, relay BSs, etc.). These different types of BSs may have different transmit power levels, different coverage areas, and different effects on interference in the wireless network 100. For example, a macro BS may have a high transmit power level (e.g., 5 watts to 40 watts), while a pico BS, a femto BS, and a relay BS may have a lower transmit power level (e.g., 0.1 watt to 2 watts).

[0039] The network controller 130 may be coupled to a group of BSs and may provide coordination and control for these BSs. The network controller 130 may communicate with the BSs via a backhaul. The BSs may also communicate with each other (eg, directly or indirectly via a wireless or wired backhaul).

[0040] UE 120 (e.g., 120a, 120b, 120c) may be dispersed throughout the wireless network 100, and each UE may be stationary or mobile. UE may also be referred to as an access terminal, terminal, mobile station, subscriber unit, station, etc. UE may be a cellular phone (e.g., a smart phone), a personal digital assistant (PDA), a wireless modem, a wireless communication device, a handheld device, a laptop computer, a cordless phone, a wireless local loop (WLL) station, a tablet computer, a camera, a gaming device, a netbook, a smartbook, an ultrabook, a medical device or equipment, a biometric sensor / device, a wearable device (smart watch, smart clothing, smart glasses, smart wristband, smart jewelry (e.g., smart ring, smart bracelet)), an entertainment device (e.g., a music or video device or a satellite radio), a component or sensor of a vehicle, a smart meter / sensor, industrial manufacturing equipment, a global positioning system device, or any other suitable device configured to communicate via a wireless or wired medium.

[0041] Some UEs may be considered as machine type communication (MTC) or evolved or enhanced machine type communication (eMTC) UEs. For example, MTC and eMTC UEs include robots, drones, remote devices, sensors, meters, monitors, location tags, etc. that can communicate with a base station, another device (e.g., a remote device), or some other entity. A wireless node may provide connectivity to or to a network (e.g., a wide area network (such as the Internet) or a cellular network), for example, via a wired or wireless communication link. Some UEs may be considered as Internet of Things (IoT) devices and / or may be implemented as NB-IoT (narrowband Internet of Things) devices. Some UEs may be considered as user premises equipment (CPE). UE 120 may be included in a housing that houses components of UE 120 (e.g., processor components, memory components, etc.).

[0042] Typically, any number of wireless networks can be deployed in a given geographic area. Each wireless network can support a specific radio access technology (RAT) and can operate on one or more frequencies. RAT can also be referred to as radio technology, air interface, etc. Frequency can also be referred to as carrier, frequency channel, etc. In a given geographic area, each frequency can support a single RAT to avoid interference between wireless networks of different RATs. In some cases, NR or 5G RAT networks can be deployed.

[0043] In some aspects, two or more UEs 120 (e.g., shown as UE 120a and UE 120e) may communicate directly (e.g., without using base station 110 as an intermediary to communicate with each other) using one or more sidelink channels. For example, UE 120 may communicate using peer-to-peer (P2P) communication, device-to-device (D2D) communication, vehicle-to-everything (V2X) protocols (e.g., which may include vehicle-to-vehicle (V2V) protocols, vehicle-to-infrastructure (V2I) protocols, etc.), mesh networks, etc. In this case, UE 120 may perform scheduling operations, resource selection operations, and / or other operations described elsewhere herein performed by base station 110. For example, base station 110 may configure UE 120 via downlink control information (DCI), radio resource control (RRC) signaling, medium access control-control element (MAC-CE), or via system information (e.g., system information block (SIB)).

[0044] The UE 120 may include a zone membership determination module 140. For simplicity, only one UE 120d is shown as including the zone membership determination module 140. The zone membership determination module 140 may receive a zone determination function based on registering a federated learning process for training a first federated learning model. The zone membership determination module 140 may also determine zone membership based on UE parameters and the zone determination function. The zone membership determination module 140 may also select the first federated learning model based on the zone membership. The zone membership determination module 140 may train the first federated learning model.

[0045] As indicated above, Figure 1 This is provided as an example only. Other examples can be found in the reference Figure 1 The examples described are different.

[0046] Figure 2 A block diagram of a design 200 of a base station 110 and a UE 120 is shown, where the base station and the UE may be Figure 1 A base station in the base station and Figure 1 Base station 110 may be equipped with T antennas 234a through 234t, and UE 120 may be equipped with R antennas 252a through 252r, where in general T≧1 and R≧1.

[0047] At the base station 110, the transmit processor 220 may receive data for one or more UEs from the data source 212, select one or more modulation and coding schemes (MCS) for each UE based at least in part on a channel quality indicator (CQI) received from the UE, process (e.g., encode and modulate) the data for the UE based at least in part on the MCS selected for each UE, and provide data symbols for all UEs. Reducing the MCS lowers throughput but increases the reliability of transmission. The transmit processor 220 may also process system information (e.g., for semi-static resource allocation information (SRPI), etc.) and control information (e.g., CQI requests, grants, upper layer signaling, etc.), and provide overhead symbols and control symbols. The transmit processor 220 may also generate reference symbols for reference signals (e.g., cell-specific reference signals (CRS)) and synchronization signals (e.g., primary synchronization signals (PSS) and secondary synchronization signals (SSS)). The transmit (TX) multiple-input multiple-output (MIMO) processor 230 may perform spatial processing (e.g., pre-decoding) on ​​data symbols, control symbols, overhead symbols, and reference symbols where applicable, and may provide T output symbol streams to T modulators (MOD) 232a to 232t. Each modulator 232 may process a corresponding output symbol stream (e.g., for orthogonal frequency division multiplexing (OFDM) or the like) to obtain an output sample stream. Each modulator 232 may further process (e.g., convert to analog, amplify, filter, and up-convert) the output sample stream to obtain a downlink signal. The T downlink signals from modulators 232a to 232t may be transmitted via T antennas 234a to 234t, respectively. According to various aspects described in more detail below, position coding may be used to generate synchronization signals to convey additional information.

[0048] At the UE 120, antennas 252a to 252r may receive downlink signals from the base station 110 and / or other base stations, and may provide received signals to demodulators (DEMODs) 254a to 254r, respectively. Each demodulator 254 may condition (e.g., filter, amplify, downconvert, and digitize) the received signal to obtain input samples. Each demodulator 254 may further process the input samples (e.g., for OFDM, etc.) to obtain received symbols. The MIMO detector 256 may obtain received symbols from all R demodulators 254a to 254r, perform MIMO detection on the received symbols (if applicable), and provide detected symbols. The receive processor 258 may process (e.g., demodulate and decode) the detected symbols, provide decoded data for the UE 120 to the data sink 260, and provide decoded control information and system information to the controller / processor 280. The channel processor may determine reference signal received power (RSRP), received signal strength indicator (RSSI), reference signal received quality (RSRQ), channel quality indicator (CQI), etc. In some aspects, one or more components of UE 120 may be included in a housing.

[0049] On the uplink, at the UE 120, a transmit processor 264 may receive data from a data source 262 and control information (e.g., for reports including RSRP, RSSI, RSRQ, CQI, etc.) from a controller / processor 280 and process the data and control information. The transmit processor 264 may also generate reference symbols for one or more reference signals. The symbols from the transmit processor 264 may be pre-decoded by a TX MIMO processor 266, if applicable, further processed by modulators 254a to 254r (e.g., for discrete Fourier transform spread OFDM (DFT-s-OFDM), CP-OFDM, etc.), and transmitted to the base station 110. At the base station 110, uplink signals from the UE 120 and other UEs may be received by the antenna 234, processed by the demodulator 254, detected by the MIMO detector 236 (if applicable), and further processed by the receive processor 238 to obtain decoded data and control information transmitted by the UE 120. The receive processor 238 may provide the decoded data to the data sink 239 and the decoded control information to the controller / processor 240. The base station 110 may include a communication unit 244 and communicate with the network controller 130 via the communication unit 244. The network controller 130 may include a communication unit 294, a controller / processor 290, and a memory 292.

[0050] The controller / processor 240 of the base station 110, the controller / processor 280 of the UE 120, and / or Figure 2 Any other components of may perform one or more techniques associated with determining membership of zone-based federated learning as described in more detail elsewhere. For example, controller / processor 240 of base station 110, controller / processor 280 of UE 120, and / or Figure 2 Any other component of the can perform or direct e.g. Figures 9 and 10 The processes and / or operations of other processes as described. Memory 242 and memory 282 may store data and program codes for base station 110 and UE 120, respectively. Scheduler 246 may schedule UEs for data transmission on the downlink and / or uplink.

[0051] In some aspects, UE 120 may include means for receiving, means for determining, means for selecting, means for training, means for tabulating, means for communicating, means for periodically determining, means for storing, and / or means for updating.

[0052] As pointed out above, Figure 2 This is provided as an example only. Other examples can be found in the reference Figure 2 The examples described are different.

[0053] In some cases, different types of devices supporting different types of applications and / or services may coexist in a cell. Examples of different types of devices include UE phones, user premises equipment (CPE), vehicles, Internet of Things (IoT) devices, etc. Examples of different types of applications include ultra-reliable low-latency communications (URLLC) applications, massive machine type communications (mMTC) applications, enhanced mobile broadband (eMBB) applications, vehicle-to-everything (V2X) applications, etc. In addition, in some cases, a single device may support different applications or services at the same time.

[0054] The deployment of a communication system (such as a 5G New Radio (NR) system) can be arranged with various components or constituent parts in a variety of ways. In a 5G NR system or network, a network node, a network entity, a mobility element of a network, a radio access network (RAN) node, a core network node, a network element or a network equipment (such as a base station (BS) or one or more units (or one or more components) that perform base station functionality) can be implemented in an aggregated or decomposed architecture. For example, a BS (such as a Node B (NB), an evolved NB (eNB), an NR BS, a 5G NB, an access point (AP), a transmit and receive point (TRP) or a cell, etc.) can be implemented as an aggregated base station (also referred to as an independent BS or a monolithic BS) or a decomposed base station.

[0055] The aggregated base station can be configured to utilize a radio protocol stack physically or logically integrated within a single RAN node. The decomposed base station can be configured to utilize a protocol stack physically or logically distributed between two or more units, such as one or more central or centralized units (CU), one or more distributed units (DU), or one or more radio units (RU). In some aspects, the CU can be implemented within a RAN node, and one or more DUs can be co-located with the CU, or alternatively, can be geographically or virtually distributed in one or more other RAN nodes. The DU can be implemented to communicate with one or more RUs. Each of the CU, DU, and RU can also be implemented as a virtual unit, namely a virtual centralized unit (VCU), a virtual distributed unit (VDU), or a virtual radio unit (VRU).

[0056] Base station type operations or network designs may take into account the aggregated nature of base station functionality. For example, a disaggregated base station may be used in an integrated access backhaul (IAB) network, an open radio access network (O-RAN (network configurations such as those initiated by the O-RAN Alliance)), or a virtualized radio access network (vRAN, also known as a cloud radio access network (C-RAN)). Decomposition may include distributing functionality across two or more units at various physical locations, as well as virtually distributing functionality of at least one unit, which may enable flexibility in network design. Individual units of a disaggregated base station or disaggregated RAN architecture may be configured for wired or wireless communication with at least one other unit.

[0057] Figure 3 A diagram illustrating an example decomposed base station 300 architecture is shown. The decomposed base station 300 architecture may include one or more central units (CUs) 310 that may communicate directly with a core network 320 via a backhaul link, or indirectly with the core network 320 through one or more decomposed base station units, such as a near real-time (near-RT) RAN intelligent controller (RIC) 325 via an E2 link, or a non-real-time (non-RT) RIC 315 associated with a service management and orchestration (SMO) framework 305, or both. The CU 310 may communicate with one or more distributed units (DUs) 330 via respective midhaul links, such as an F1 interface. The DU 330 may communicate with one or more radio units (RUs) 340 via respective fronthaul links. The RU 340 may communicate with respective UEs 120 via one or more radio frequency (RF) access links. In some implementations, a UE 120 may be served simultaneously by multiple RUs 340.

[0058] Each of these units (e.g., CU 310, DU 330, RU 340, and near-RT RIC 325, non-RTRIC 315, and SMO framework 305) may include one or more interfaces, or may be coupled to one or more interfaces configured to receive or send signals, data, or information (collectively referred to as signals) via a wired or wireless transmission medium. Each of these units or an associated processor or controller that provides instructions to the communication interface of these units may be configured to communicate with one or more of the other units via a transmission medium. For example, these units may include a wired interface that is configured to receive or send signals to one or more of the other units via a wired transmission medium. Additionally, these units may include a wireless interface that may include a receiver, a transmitter, or a transceiver (such as a radio frequency (RF) transceiver) that is configured to receive or send signals, or both, to one or more of the other units on a wireless transmission medium.

[0059] In some aspects, CU 310 may host one or more higher layer control functions. Such control functions may include radio resource control (RRC), packet data convergence protocol (PDCP), service data adaptation protocol (SDAP), etc. Each control function may be implemented using an interface configured to communicate signals with other control functions hosted by CU 310. CU 310 may be configured to handle user plane functionality (i.e., central unit-user plane (CU-UP)), control plane functionality (i.e., central unit-control plane (CU-CP)), or a combination thereof. In some specific implementations, CU 310 may be logically split into one or more CU-UP units and one or more CU-CP units. When implemented in an O-RAN configuration, the CU-UP unit may communicate bidirectionally with the CU-CP unit via an interface (such as an E1 interface). CU 310 may be implemented to communicate with DU 330 as needed for network control and signaling.

[0060] DU 330 may correspond to a logical unit that includes one or more base station functions for controlling the operation of one or more RU 340. In some aspects, DU 330 may host one or more of a radio link control (RLC) layer, a medium access control (MAC) layer, and one or more high physical (PHY) layers (such as modules for forward error correction (FEC) encoding and decoding, scrambling, modulation and demodulation, etc.) at least in part according to a functional split such as defined by the Third Generation Partnership Project (3GPP). In some aspects, DU 330 may also host one or more low PHY layers. Each layer (or module) may be implemented using an interface that is configured to communicate signals with other layers (and modules) hosted by DU 330 or with control functions hosted by CU 310.

[0061] The lower layer functionality may be implemented by one or more RUs 340. In some deployments, a RU 340 controlled by a DU 330 may correspond to a logical node that hosts RF processing functions or low PHY layer functions (such as performing Fast Fourier Transform (FFT), Inverse FFT (iFFT), digital beamforming, physical random access channel (PRACH) extraction and filtering, etc.), or both, based at least in part on a functional split such as a lower layer functional split. In such an architecture, the RU 340 may be implemented to handle over-the-air (OTA) communications with one or more UEs 120. In some implementations, real-time and non-real-time aspects of control plane and user plane communications with the RU 340 may be controlled by the corresponding DU 330. In some scenarios, this configuration may enable the DU 330 and the CU 310 to be implemented in a cloud-based RAN architecture, such as a vRAN architecture.

[0062] The SMO framework 305 may be configured to support RAN deployment and provisioning of non-virtualized network elements and virtualized network elements. For non-virtualized network elements, the SMO framework 305 may be configured to support the deployment of dedicated physical resources for RAN coverage requirements, which may be managed via an operation and maintenance interface (such as an O1 interface). For virtualized network elements, the SMO framework 305 may be configured to interact with a cloud computing platform (such as an open cloud (O-Cloud) 390) to perform network element lifecycle management (such as instantiating virtualized network elements) via a cloud computing platform interface (such as an O2 interface). Such virtualized network elements may include, but are not limited to, CU 310, DU 330, RU 340, and near-RT RIC 325. In some specific implementations, the SMO framework 305 may communicate with hardware aspects of the 4G RAN (such as an open eNB (O-eNB) X11) via an O1 interface. Additionally, in some specific implementations, the SMO framework 305 may communicate directly with one or more RUs 340 via an O1 interface. The SMO framework 305 may also include a non-RT RIC 315 configured to support the functionality of the SMO framework 305 .

[0063] The non-RT RIC 315 may be configured to include logic functions that enable non-real-time control and optimization of RAN elements and resources, artificial intelligence / machine learning (AI / ML) workflows including model training and updating, or policy-based guidance of applications / features in the near-RT RIC 325. The non-RT RIC 315 may be coupled to or in communication with the near-RT RIC 325 (such as via an A1 interface). The near-RT RIC 325 may be configured to include logic functions that enable near-real-time control and optimization of RAN elements and resources via data collection and actions through an interface (such as via an E2 interface) that connects one or more CUs 310, one or more DUs 330, or both, and the O-eNB with the near-RT RIC 325.

[0064] In some implementations, in order to generate an AI / ML model to be deployed in the near-RT RIC 325, the non-RT RIC 315 may receive parameters or external enrichment information from an external server. Such information may be utilized by the near-RT RIC 325 and may be received from a non-network data source or from a network function at the SMO framework 305 or the non-RT RIC 315. In some examples, the non-RT RIC 315 or the near-RT RIC 325 may be configured to tune RAN behavior or performance. For example, the non-RT RIC 315 may monitor long-term trends and patterns of performance and employ AI / ML models to perform corrective actions through the SMO framework 305 (such as via reconfiguration of O1) or via the creation of RAN management policies (such as A1 policies).

[0065] Figure 4 An example implementation of a system on chip (SOC) 400 according to certain aspects of the present disclosure is illustrated, which may include a central processing unit (CPU) 402 or a multi-core CPU configured to generate gradients for neural network training. The SOC 400 may be included in a base station 110 or a UE 120. Variables (e.g., neural signals and synaptic weights), system parameters associated with a computing device (e.g., a neural network with weights), delays, frequency bin information, and task information may be stored in a memory block associated with a neural processing unit (NPU) 408, a memory block associated with a CPU 402, a memory block associated with a graphics processing unit (GPU) 404, a memory block associated with a digital signal processor (DSP) 406, a memory block 418, or may be distributed across multiple blocks. Instructions executed at the CPU 402 may be loaded from a program memory associated with the CPU 402, or may be loaded from a memory block 418.

[0066] The SOC 400 may also include additional processing blocks tailored for specific functions, such as a GPU 404, a DSP 406, a connectivity block 410 (which may include fifth generation (5G) connectivity, fourth generation long term evolution (4G LTE) connectivity, Wi-Fi connectivity, USB connectivity, Bluetooth connectivity, etc.), and a multimedia processor 412 that may, for example, detect and recognize gestures. In one specific implementation, the NPU is implemented in the CPU, DSP, and / or GPU. The SOC 400 may also include a sensor processor 414, an image signal processor (ISP) 416, and / or a navigation module 420, which may include a global positioning system.

[0067] The SOC 400 may be based on the ARM instruction set. In one aspect of the present disclosure, the instructions loaded into the general processor 402 may include code for receiving a zone determination function by a user equipment (UE) based on a joint learning process for training a first joint learning model by registering. The general processor 402 may also include code for determining zone membership by the UE based on UE parameters and the zone determination function. The general processor 402 may also include code for selecting a first joint learning model by the UE based on zone membership. The general processor 402 may include code for training a first joint learning model by the UE.

[0068] Deep learning architectures can perform object recognition tasks by learning to represent inputs at successively higher levels of abstraction in each layer, thereby building useful feature representations of the input data. In this way, deep learning solves the main bottleneck of traditional machine learning. Before the advent of deep learning, machine learning methods for object recognition problems may rely heavily on human-designed features, possibly in conjunction with shallow classifiers. A shallow classifier can be a two-class linear classifier, for example, in which the weighted sum of feature vector components can be compared to a threshold to predict which class the input belongs to. Human-designed features can be templates or kernels customized for a specific problem domain by engineers with domain expertise. In contrast, while deep learning architectures can learn to represent features similar to those that human engineers might design, they require training. In addition, deep networks can learn to represent and recognize new types of features that humans may not have considered.

[0069] Deep learning architectures can learn hierarchies of features. For example, if presented with visual data, the first layer can learn to recognize relatively simple features in the input stream, such as edges. In another example, if presented with auditory data, the first layer can learn to recognize spectral power in specific frequencies. The second layer, taking the output of the first layer as input, can learn to recognize combinations of features, such as simple shapes for visual data or combinations of sounds for auditory data. For example, higher layers can learn to represent complex shapes in visual data or words in auditory data. Even higher layers can learn to recognize common visual objects or spoken phrases.

[0070] Deep learning architectures can perform particularly well when applied to problems that have a natural hierarchical structure. For example, the classification of motorized vehicles can benefit from first learning to recognize wheels, windshields, and other features. These features can be combined in different ways at higher levels to recognize cars, trucks, and airplanes.

[0071] Neural networks can be designed to have a variety of connectivity patterns. In a feedforward network, information is passed from a lower layer to a higher layer, where each neuron in a given layer communicates with a neuron in a higher layer. As described above, hierarchical representations can be constructed in successive layers of a feedforward network. Neural networks can also have loops or feedback (also known as top-down) connections. In a loop connection, the output from a neuron in a given layer can be communicated to another neuron in the same layer. The loop architecture can help identify patterns that span more than one input data block in the input data blocks that are sequentially delivered to the neural network. The connection from a neuron in a given layer to a neuron in a lower layer is called a feedback (or top-down) connection. When the recognition of a high-level concept can assist in discerning specific low-level features of the input, a network with many feedback connections may be helpful.

[0072] The connections between neural network layers can be fully connected or partially connected. Figure 5A An example of a fully connected neural network 502 is illustrated. In a fully connected neural network 502, a neuron in a first layer may communicate its output to each neuron in a second layer, such that each neuron in the second layer will receive input from each neuron in the first layer. Figure 5B An example of a locally connected neural network 504 is illustrated. In the locally connected neural network 504, neurons in a first layer may be connected to a limited number of neurons in a second layer. More generally, the locally connected layers of the locally connected neural network 504 may be configured such that each neuron in the layer will have the same or similar connectivity pattern, but the connection strengths may have different values ​​(e.g., 510, 512, 514, and 516). The locally connected connectivity patterns may produce spatially different receptive fields in higher layers because higher layer neurons in a given area may receive inputs that are tuned through training to the characteristics of a limited portion of the total input to the network.

[0073] An example of a locally connected neural network is a convolutional neural network. Figure 5C An example of a convolutional neural network 506 is illustrated. The convolutional neural network 506 can be configured such that the connection strengths associated with the inputs of each neuron in the second layer are shared (e.g., 508). Convolutional neural networks may be well suited for problems where the spatial location of the inputs is meaningful.

[0074] One type of convolutional neural network is a deep convolutional network (DCN). Figure 5DA detailed example of a DCN 500 designed to recognize visual features from an image 526 input from an image capture device 530 (such as a vehicle-mounted camera) is illustrated. The DCN 500 of the current example can be trained to identify traffic signs and numbers provided on traffic signs. Of course, the DCN 500 can be trained for other tasks, such as identifying lane markings or identifying traffic lights.

[0075] The DCN 500 may be trained by supervised learning. During training, an image (such as an image 526 of a speed limit sign) may be presented to the DCN 500, and a forward pass may then be calculated to produce an output 522. The DCN 500 may include a feature extraction portion and a classification portion. Upon receiving the image 526, a convolutional layer 532 may apply a convolutional kernel (not shown) to the image 526 to generate a first set of feature maps 518. As an example, the convolutional kernel of the convolutional layer 532 may be a 5x5 kernel that generates a 28x28 feature map. In this example, because four different feature maps are generated in the first set of feature maps 518, four different convolutional kernels are applied to the image 526 at the convolutional layer 532. A convolutional kernel may also be referred to as a filter or a convolutional filter.

[0076] The first set of feature maps 518 may be subsampled by a max pooling layer (not shown) to generate a second set of feature maps 520. The max pooling layer reduces the size of the first set of feature maps 518. That is, the size of the second set of feature maps 520 (such as 14x14) is smaller than the size of the first set of feature maps 518 (such as 28x28). The reduced size provides similar information to subsequent layers while reducing memory consumption. The second set of feature maps 520 may be further convolved via one or more subsequent convolutional layers (not shown) to generate one or more sets of subsequent feature maps (not shown).

[0077] exist Figure 5D In the example of , the second set of feature maps 520 are convolved to generate a first feature vector 524. In addition, the first feature vector 524 is further convolved to generate a second feature vector 528. Each feature of the second feature vector 528 can include a number corresponding to a possible feature of the image 526, such as "sign", "60", and "100". A softmax function (not shown) can convert the numbers in the second feature vector 528 into probabilities. Therefore, the output 522 of the DCN 500 can be the probability that the image 526 includes one or more features.

[0078] In this example, the probability of "logo" and "60" in output 522 is higher than the probability of other numbers (such as "30", "40", "50", "70", "80", "90", and "100") in output 522. Before training, the output 522 generated by DCN 500 may be incorrect. Therefore, the error between the output 522 and the target output can be calculated. The target output is the ground truth of image 526 (e.g., "logo" and "60"). The weights of DCN 500 can then be adjusted so that the output 522 of DCN 500 is closer to the target output.

[0079] To adjust the weights, the learning algorithm may calculate a gradient vector for the weights. The gradient may indicate the amount by which the error will increase or decrease when the weights are adjusted. At the top layer, the gradient may correspond directly to the value of the weights connecting the activated neurons in the penultimate layer and the neurons in the output layer. In lower layers, the gradient may depend on the value of the weights and the calculated error gradients of the higher layers. The weights may then be adjusted to reduce the error. This way of adjusting weights may be referred to as "backward propagation" because it involves a "backward pass" through the neural network.

[0080] In practice, the error gradient of the weights may be calculated over a small number of examples so that the calculated gradient is close to the true error gradient. This approximation method may be referred to as stochastic gradient descent. Stochastic gradient descent may be repeated until the achievable error rate of the entire system stops decreasing or until the error rate reaches a target level. After learning, a new image (e.g., a speed limit sign of image 526) may be presented to DCN 500, and a forward pass through DCN 500 may produce output 522, which may be considered an inference or prediction of DCN 500.

[0081] A Deep Belief Network (DBN) is a probabilistic model that includes multiple layers of hidden nodes. A DBN can be used to extract a hierarchical representation of a training data set. A DBN can be obtained by stacking layers of Restricted Boltzmann Machines (RBMs). RBMs are a type of artificial neural network that can learn a probability distribution over a set of inputs. Because RBMs can learn probability distributions without information about the category to which each input should be classified, RBMs are often used for unsupervised learning. Using a hybrid unsupervised and supervised paradigm, the bottom RBM of a DBN can be trained in an unsupervised manner and can be used as a feature extractor, while the top RBM can be trained in a supervised manner (on the joint distribution of inputs from the previous layer and the target class) and can be used as a classifier.

[0082] A DCN is a network of convolutional networks, configured with additional pooling and normalization layers. DCN achieves state-of-the-art performance on many tasks. DCN can be trained using supervised learning, where both the input and output targets are known for many examples and are used to modify the weights of the network by using a gradient descent method.

[0083] The DCN may be a feed-forward network. In addition, as described above, the connections from a neuron in the first layer of the DCN to a set of neurons in the next higher layer are shared across the neurons in the first layer. The feed-forward and shared connections of the DCN may be used for fast processing. For example, the computational burden of the DCN may be much smaller than that of a similarly sized neural network that includes loops or feedback connections.

[0084] The processing of each layer of the convolutional network can be thought of as a spatially invariant template or basis projection. If the input is first decomposed into multiple channels, such as the red, green, and blue channels of a color image, then the convolutional network trained on this input can be thought of as three-dimensional, where two spatial dimensions are along the axes of the image and the third dimension captures color information. The output of the convolutional connection can be thought of as forming a feature map in a subsequent layer, where each element in the feature map (e.g., 220) receives input from a range of neurons in the previous layer (e.g., feature map 218) and from each of the multiple channels. The values ​​in the feature map can be further processed with nonlinearities (such as correction, max(0,x)). Values ​​from neighboring neurons can be further pooled, which corresponds to downsampling and can provide additional local invariance and dimensionality reduction. Normalization corresponding to whitening can also be applied by lateral inhibition between neurons in the feature map.

[0085] The performance of deep learning architectures can increase as more labeled data points become available or as computing power increases. Modern deep neural networks are often trained with computing resources that are thousands of times greater than what was available to a typical researcher just fifteen years ago. New architectures and training paradigms can further improve the performance of deep learning. Rectified linear units can reduce the training problem known as vanishing gradients. New training techniques can reduce overfitting, allowing larger models to achieve better generalization. Encapsulation techniques can extract data within a given receptive field and further improve overall performance.

[0086] Figure 6 650 is a block diagram illustrating a DCN 650. Based on connectivity and weight sharing, the deep convolutional network 650 may include multiple different types of layers. Figure 6As shown, the deep convolutional network 650 includes convolutional blocks 654A, 654B. Each of the convolutional blocks 654A, 654B may be configured with a convolutional layer (CONV) 656, a normalization layer (LNorm) 658, and a maximum pooling layer (MAXPOOL) 660. Although only two convolutional blocks 654A, 654B are shown, the present disclosure is not limited thereto, but instead, any number of convolutional blocks 654A, 654B may be included in the deep convolutional network 650 according to design preferences.

[0087] The convolution layer 656 may include one or more convolution filters that may be applied to the input data to generate a feature map. The normalization layer 658 may normalize the output of the convolution filter. For example, the normalization layer 658 may provide whitening or lateral suppression. The maximum pooling layer 660 may provide spatial downsampling aggregation to achieve local invariance and dimensionality reduction.

[0088] For example, a parallel filter bank of a deep convolutional network can be loaded on SOC 400 (e.g., Figure 4 ) on the CPU 402 or GPU 404 of the SOC 400 to achieve high performance and low power consumption. In an alternative embodiment, the parallel filter bank can be loaded onto the DSP 406 or ISP 416 of the SOC 400. In addition, the deep convolutional network 650 can access other processing blocks that may exist on the SOC 400, such as the sensor processor 414 and the navigation module 420 dedicated to sensors and navigation, respectively.

[0089] The deep convolutional network 650 may also include one or more fully connected layers 662 (FC1 and FC2). The deep convolutional network 650 may also include a logistic regression (LR) layer 664. There are weights (not shown) to be updated between each layer 656, 658, 660, 662, 664 of the deep convolutional network 650. The output of each of these layers (e.g., 656, 658, 660, 662, 664) can be used as an input to a subsequent layer of these layers (e.g., 656, 658, 660, 662, 664) in the deep convolutional network 650 to learn a hierarchical feature representation from the input data 652 (e.g., image, audio, video, sensor data, and / or other input data) supplied at the first convolutional block 654A. The output of the deep convolutional network 650 is a classification score 666 for the input data 652. The classification score 666 can be a set of probabilities, where each probability is a probability of the input data, including a feature from a feature set.

[0090] Federated learning is a machine learning technique that trains a federated learning model across multiple decentralized edge devices or servers that maintain local data samples without sharing the data samples with the server. Federated learning provides the benefits of privacy-preserving machine learning and continuous learning on the edge. However, when the data at the device is non-independent and identically distributed (non-IID), the performance of federated learning is impaired. Data augmentation is a method to address non-IID data. Another method is zone-based federated learning. Zone-based federated learning groups participating devices into zones that contribute to the distribution of non-IID data at the edge. Aspects of the present disclosure include a method for determining zone membership of devices participating in a federated learning process for training a federated learning model.

[0091] Figure 7 is a diagram illustrating an example zone network topology 700 for zone-based federated learning according to aspects of the present disclosure. Figure 7 , the example zone network topology 700 includes two zones, namely, zone 1 704a and zone 2 704b. For the sake of brevity and simplicity of illustration, only two zones are shown, however, the zone network topology 700 may include more than two zones. Each of the zones 704a, 704b may include multiple participating devices 710a-710f. Each of the participating devices 710a-710f may be a mobile communication device, such as, for example, a smart phone or an electric vehicle, or an Internet of Things (IoT) device. Each of the participating devices 710a-710f may be included in a group corresponding to a zone (e.g., 704a or 704b) based on one or more common attributes or settings. In some examples, the participating devices (e.g., 710a-710f) may be in more than one group ( Figure 7 Additionally or alternatively, two or more zones may overlap ( Figure 7 As described, the properties and settings may include, but are not limited to, geographic location, default language, or user interface theme. As an example, each zone 704a or 704b may be based on the geographic location of participating devices 710a-710f.

[0092] Each of the participating devices 710a-710f can be docked and communicated with one or more communicator edge nodes (e.g., 706, 708a, and 708b). In some aspects, the communicator edge nodes (e.g., 706, 708a, and 708b) can also act as an aggregator for a given zone (e.g., 704a or 704b). The aggregator can be configured to perform zone-level joint averaging. That is, the aggregator can receive model updates calculated at each of the participating devices (e.g., 710a-710f) in the zone (e.g., 704a or 704b), and can calculate a representative value of the zone, such as an average value. For example, the communicator edge node 708a can also act as an aggregator for zone 1 704a. On the other hand, the communicator edge node 708b can also be used as an aggregator for zone 2 704b. In some aspects, the communicator edge nodes (e.g., 706, 708a, and 708b) and the aggregator node can be a base station (e.g., gNode B). For example, in 5G NR and later deployments, mobile edge computing (MEC) devices may be used as aggregators (e.g., 708a, 708b) or communicators (e.g., 706, 708a, and 708b).

[0093] Each zone (e.g., 704a, 704b) may include one or more communicator edge nodes (e.g., 706) and an aggregator (e.g., 708a, 708b) that also operates as a communicator edge node. The aggregator (e.g., 708a, 708b) may receive a global model from the cloud device 702. The aggregator (e.g., 708a, 708b) may distribute the global model to each of the participating devices (e.g., 710a-710f) in the zone. Each of the participating devices (e.g., 710a-710f) may be trained with the global model to generate a local model. Since each device (e.g., 710a-710f) may collect data and operate a local model, each of the participating devices may be retrained (e.g., according to a loss function) to generate a local model update. Each of the aggregators (e.g., 708a, 708b) may receive local model updates from each of the devices (e.g., 710a-710f) in their respective zones (e.g., 704a, 704b). For example, aggregator 708a may receive local model updates from each of the devices 710a and 710b. Aggregator 708a may aggregate the local model updates and compute the zone model updates, for example, using a joint averaging process, etc. The aggregator (e.g., 708a) may then provide the zone model updates to each of the participating devices (e.g., 710a-710b) in the zone (e.g., 704a). In addition, the aggregator (e.g., 708a, 708b) may provide the zone model updates to the cloud device 702 that manages the global model. The updates (e.g., local model updates, zone model updates) may include all model weights, changed model weights, incremental values ​​of model weights, or in some cases the entire model.

[0094] Figure 8 8 is a block diagram illustrating an example of a participating device 800 including a federated learning (FL) telephony manager 802 according to aspects of the present disclosure. Figure 8 In the example of FIG. 8 , the participating device 800 may be an example of a UE, such as referring to Figure 1 , Figure 2 , Figure 3 and Figure 7 UE 120, 710 (710a-710f) described. Participating device 800 can communicate with at least one network device in zone 850, which includes FL zone manager 852 (only one network device with a zone manager is shown in this example). The network device in each zone 850 can be an example of base station 110, such as reference 100, ... Figure 1 , Figure 2 , Figure 3 and Figure 7The base stations 110, 706, 708 (708a, 708b) described. The network devices in the zone 850 including the FL zone manager 852 can communicate with the network devices in the cloud 870 including the zone partition keeper 872. The network devices in the cloud 870 having the zone partition keeper 872 can be examples of the cloud devices 702, as described in reference Figure 7 As described above, the cloud device is not limited thereto.

[0095] like Figure 8 As shown in FIG. 8 , the participating device 800 may include multiple components, such as a phone local model weight storage area 804, a phone global model weight storage area 814, a model trainer 806, a model runner 816, a processed data storage area 808, a data application 810, a raw data storage area 812, an inter-process communication component 818, a data collector 822, and a local privacy protection manager 824. The various storage components 804, 808, 812, 814 may be the same storage device (such as, for example, see Figure 2 In another example, the storage components 804, 808, 812, 814 may be different storage devices. An inter-process communication component 818 (such as a bus or controller / processor) may facilitate communication between the different components 804, 806, 808, 810, 812, 814, 816. The inter-process communication component 818 may be as described with reference to Figure 2 An example of the controller / processor 280 is depicted. The application using interface 820 represents an interface (e.g., an application programming interface (API)) that can be used by applications (e.g., third-party applications) to communicate with the FL telephony manager 802 and related components 802, 804, 806, 808, 810, 812, 814, 816, 818, 822, 824 in order to participate in joint training or run inference through models managed by the FL telephony manager 802.

[0096] In some examples, the FL phone manager 802 controls data collection using one or more data collectors 822. Each data collector 822 can collect data from sensors ( Figure 8In some implementations, the data collector 822 can be embedded with another data collector 822 so that the two data collectors 822 collect different types of data at the same time. Controlling data collection via the FL phone manager 802 can improve resource usage, such as battery usage and / or processor usage, because the FL phone manager 802 can prevent multiple data collectors 822 from collecting the same data. In addition, sensor access control can be simplified based on the FL phone manager 802 controlling data collection. In some examples, the FL phone manager 802 can dynamically (e.g., on demand) configure sensor types, sampling rates, and the number of sensors used to store data from the storage ( Figure 8 The FL phone manager 802 may include one or more of the following periods during which the data is flushed to a storage area such as the processed data storage area 808 (not shown). Each model may inform the FL phone manager 802 of the type of data required for its training and the specified sampling rate. Based on the information provided by each model, the FL phone manager 802 may identify the appropriate data collector 822 to invoke and the corresponding sampling rate. In some implementations, the FL phone manager 802 may use one or more strategies to balance sensing accuracy (e.g., sampling rate) with resource consumption (e.g., battery usage, process load, etc.).

[0097] exist Figure 8 In the example of Figure 8 The FL phone manager 802 may store data obtained by the data collector 822 (not shown) in the raw data storage area 812. In addition, the data collector 822 may notify the FL phone manager 802 when new data is added to the raw data storage area 812. In some examples, the data collector 822 may buffer a certain amount of sensed data in a memory before submitting the sensed data to the raw data storage area 812. The FL phone manager 802 may dynamically reconfigure a data dump period that defines when data is written to the raw data storage area 812. In such examples, the data dump period may be initially set by the data collector 822.

[0098] In some examples, the model may use the raw data. In other examples, the model may specify additional processing for the raw data. The additional processing may be performed by data processor 810. Figure 8800. In some examples, the FL phone manager 802 can determine when to call a model-specific data processor 810. Each data processor 810 can store data in a processed data storage area 808. Data can be stored at certain intervals or based on new data becoming available in the raw data storage area 812. In some examples, all data is pre-processed before initiating a new local model training operation.

[0099] In some examples, data processor 810 and data collector 822 may be implemented by third-party developers. In some such examples, FL phone manager 802 may interact with third-party components using inter-process communication (IPC) component 818 functionality provided by the phone's operating system.

[0100] As described, the FL phone manager 802 can initiate a model trainer for a given model and determine the location of the data in the processed data storage area 808 or the raw data storage area 812. After training is complete, the model trainer 806 can store the newly calculated weights in the phone-local model weight storage area 804. In addition, the FL phone manager 802 can determine when the stored weights can be uploaded to the network device.

[0101] In some examples, the FL phone manager 802 can receive multiple models from one or more FL zone managers 852. That is, multiple models (e.g., federated learning models or applications) can be provided to the participating device 800. As an example, the first application can be a text prediction model and the second application can be a location-based advertising model. In such examples, the FL phone manager 802 can determine the training time for each model. In some examples, the participating device 800 can be associated with two different zone managers, where each zone server is associated with a different zone. Each zone server can send a different model. As another example, a single zone server can send two or more different zone models.

[0102] The models may be stored in the model trainer 806. The local weights for each model may be stored in the phone local model weight storage area 804, and the global weights may be stored in the phone global model weight storage area 814. The model weights and model parameters may be referred to as federated learning data compared to the local training data (raw or processed). In some implementations, the FL phone manager 802 may work in conjunction with one or more components 804, 806, 808, 810, 812, 814, 816 of the participating device 800 to determine the training priority of the various models stored in the model trainer 806. In some examples, the priority of the model may be determined based on various criteria, such as, but not limited to, one or more of the following: the number of samples available for training for a given model, the current accuracy of the model, an estimated model training time determined based on previous training times, and whether the training can be successfully completed based on current resource availability (e.g., battery level, current system load, etc.).

[0103] Additionally, the FL phone manager 802 can manage the local training states of the various models stored in the model trainer 806. As an example, the FL phone manager 802 can stop training a first model and start training a second model. In such an example, the FL phone manager 802 can store the local weights of the first model in the phone local model weight storage area 804 to maintain the training state of the first model so that the training can be resumed at a later time.

[0104] In some implementations, the FL phone manager 802 can determine current device resources to evaluate whether one or more models can be trained locally (e.g., on the device). It may be desirable to train the model locally to protect data privacy. Since participating devices 800 such as UEs and edge devices may have a limited number of resources, local training may still be limited. In such implementations, if the current device resources meet the resource condition and the current connectivity state meets the connection condition, the FL phone manager 802 can use the local privacy protection manager 824.

[0105] As described, the amount of available resources (such as available memory or processor load) can prevent the participating device 800 from training the model locally. In this example, the resource condition can be met when the amount of available resources prevents local training. That is, the amount of available resources can be less than a threshold. In some examples, when the resource condition is met, the FL phone manager 802 can determine the current connectivity state. The connectivity state refers to the connection state between the participating device 800 and the network device through a communication channel (such as a Wi-Fi channel or a cellular channel). In this example, the connection condition can be met if the participating device can communicate with the network device (e.g., an inter-network or intra-network device) through the communication channel. In this example, the FL phone manager 802 can use the network device as a proxy for training the model.

[0106] In some specific implementations, the local privacy protection manager 824 can be controlled individually by each participating device 800 to increase the speed of training while still protecting privacy. The local privacy protection manager 824 can be a network device that can receive both the model and the training data. The network device can train the model and return the trained weights and biases to the participating devices. In some examples, the local privacy protection manager 824 can delete the data corresponding to the model, weights, and biases after the training session. In addition, in some examples, the local privacy protection manager 824 may not understand the overall context of the model. Instead, the local privacy protection manager 824 may only be responsible for training the model. In addition, the global server may not know the local privacy protection manager 824. Because of the decentralized nature of training, and because the local privacy protection manager 824 is unaware of the entire context, the privacy of participating devices can be protected.

[0107] The zone partition maintainer 872 communicates with each FL zone manager 852. The zone partition maintainer 872 includes a zone partition assignment module 874 that maintains an overall zone topology map. The overall zone topology map identifies the zones and the FL zone manager 852 for each zone.

[0108] The FL zone manager 852 is responsible for communicating with participating devices 800 such as smart phones and performing zone-level aggregation. The FL zone manager 852 also interacts with neighbors to perform merge or split operations. The FL zone manager 852 updates the latest zone partition information to the zone partition holder 872. These zones can be adapted to improve the overall model accuracy.

[0109] In some aspects of the present disclosure, when enough updates have been uploaded (e.g., a threshold number of updates is met) or when a training round timer expires, the FL zone manager 852 calls the model aggregator 854 for the model. The model aggregator 854 reads the updates from the zone local model weight storage area 856, calculates the aggregate weights, and stores them in the zone global model weight storage area 858. Intermediate training states are stored in the training state storage 860 to provide lower input / output (I / O) latency compared to other types of cloud storage in the design. This is because the FL zone manager 852 needs to access data frequently during training. Next, the model aggregator 854 transmits a notification via the new model / zone partition notification service 862 to let the participating devices 800 know that a new model version is available. The zone local model utility storage area 864 and the zone partition updater 866 are used for model validation and zone management.

[0110] When a participating device 800 registers to participate in federated learning, the latest zone topology map and the "zone determination function" are provided to the participating device 800. This function accepts a set of parameters from the device and returns the zone information to which the device belongs. These parameters may include, for example, global positioning system (GPS) coordinates. This function can run offline and can be local to each participating device 800.

[0111] A participating device 800 periodically checks its zone membership and tabulates its training data based on the zone membership. When a participating device 800 is ready to perform local training, the participating device 800 communicates with the FL zone manager 852 for the zone to which the device belongs. Whenever the zone topology or zone determination function changes, the zone partitioning maintainer 872 updates and notifies all participating devices 800.

[0112] In other aspects, the device (e.g., 800) stores training data and parameters used by the zone membership function. For example, if an attempt is made to train a human activity recognition (HAR) model using sensor data, and if the zone partition holder provides a zone determination function that accepts GPS coordinates as parameters, the device can store the raw sensor data along with the GPS information in a sequential or time-stamped manner. When the device is ready to perform local training, the device can use the GPS data included in the data sample to determine which zone the data will be used for. These aspects differ from existing methods in that, in existing methods, the device determines zone membership when collecting data, and then tabulates the data. The previously described method involves periodic lookups of zone membership. In a second method, the device collects training data and parameters for determining zone membership. The data is partitioned to match zones at a later point in time.

[0113] Zone membership checks may be performed periodically or in an event-driven manner. According to aspects of the present disclosure, the device stores locally generated training, testing, and validation data to reflect the zone in which the data was collected. The zone determination functionality may be used in an offline mode (e.g., not connected to a network). According to aspects of the present disclosure, a participating device 800 maintains storage even when not connected to a network (e.g., moved from zone 1 to zone 2). When connectivity is restored, previously stored training weights may be uploaded to the zone 1 manager even when the participating device 800 has moved to a different zone (e.g., zone 2).

[0114] Fig. 9 is a timeline illustrating a zone membership check in accordance with aspects of the present disclosure. Fig. 9 In the example of FIG. 8 , at time t1, participating device 800 performs a periodic zone membership check using the zone determination function. At time t1, participating device 800 determines that it is a member of zone 1. Therefore, participating device 800 stores any locally generated training, testing, and validation data to reflect the data collected in zone 1. At times t2 and t3, participating device 800 again performs a periodic zone membership check. At times t2 and t3, participating device 800 is still a member of zone 1. Therefore, participating device 800 stores the locally generated data collected at these times (e.g., t2, t3) to reflect the data collected in zone 1.

[0115] At time t4, an event-driven zone check occurs. For example, a sensor-based handover or different types of activities can trigger this event-driven zone check. An accelerometer is an example of a type of sensor that can trigger an event-driven zone check. At time t4, the participating device 800 determines that it is now a member of zone 2. Therefore, the data collected at this time is stored with reference to zone 2. At time t5, the participating device 800 performs another periodic zone check. At time t5, the participating device 800 is still in zone 2 and stores data accordingly. At time t6, the periodic zone check indicates that the participating device 800 is now in zone 3. Therefore, the participating device 800 stores its data with reference to zone 3. Once the participating device 800 is ready to perform local training, the participating device 800 communicates with the joint learning zone manager 852 of the zone for which it has collected local data. In other words, the participating device 800 extracts the latest joint learning model of the zone of which the participating device 800 is a member. The participating device 800 can then perform local training and upload model updates.

[0116] As shown above, Figures 4 to 9 Provided as an example. Other examples may be relevant to Figures 4 to 9 The examples described are different.

[0117] Fig.101 is a flow chart illustrating an example process 1000 for determining zone membership in zone-based federated learning according to aspects of the present disclosure. The example process 1000 is an example of determining zone membership in zone-based federated learning. The operations of process 1000 may be implemented by a UE (e.g., UE 120, 710 (710a-710f), participating device 800, etc.).

[0118] At block 1002, the UE receives a zone determination function based on registering a federated learning process for training a first federated learning model. For example, the UE (e.g., using antenna 252, MOD / DEMOD 254, MIMO detector 256, receive processor 258, controller / processor 280, and / or memory 282) may receive the zone determination function. In some aspects, the UE also receives an updated zone topology map from a zone partitioning retainer, the updated zone topology map indicating an updated federated learning zone manager for each zone. The zone determination function and the topology map may be received at any time before the device performs local training.

[0119] At block 1004, the UE determines zone membership based on the UE parameters and the zone determination function. For example, the UE (e.g., using the controller / processor 280 and / or the memory 282) may determine the zone membership. In some aspects, the UE periodically determines the zone membership. In other aspects, the UE determines the zone membership in response to a triggering event. The UE may also receive an updated zone determination function from a zone partitioning maintainer.

[0120] At block 1006, the UE selects a first federated learning model based on the zone membership. For example, the UE (e.g., using the controller / processor 280 and / or the memory 282) may select the first federated learning model. In some aspects, the UE may also select a second federated learning model for inference based on the zone membership.

[0121] At block 1008, the UE trains the first joint learning model. For example, the UE (e.g., using the controller / processor 280 and / or the memory 282) may train the first joint learning model. In some aspects, the UE stores sensor data associated with parameters, such as location data or user purchase transaction history. The UE may also determine data samples for training with respect to a particular zone based on the parameters associated with the sensor data.

[0122] Example aspects

[0123] Aspect 1: A processor-implemented method, the method comprising: receiving, by a user equipment (UE), a zone determination function based on registering a federated learning process for training a first federated learning model; determining, by the UE, zone membership based on UE parameters and the zone determination function; selecting, by the UE, the first federated learning model based on the zone membership; and training the first federated learning model by the UE.

[0124] Aspect 2: The method according to aspect 1, further comprising: tabulating training data based on the zone membership; and communicating with a federated learning zone manager corresponding to the zone membership.

[0125] Aspect 3: The method according to aspect 1 or 2, further comprising: receiving an updated zone determination function from a zone division holder.

[0126] Aspect 4: The method according to any one of the preceding aspects, further comprising: receiving an updated zone topology map from a zone partitioning retainer, the updated zone topology map indicating an updated joint learning zone manager for each zone.

[0127] Aspect 5: The method according to any of the preceding aspects, further comprising periodically determining the zone membership.

[0128] Aspect 6: The method according to any one of the preceding aspects, further comprising: storing sensor data associated with parameters; and determining data samples for training on a specific area based on the parameters associated with the sensor data.

[0129] Aspect 7: The method according to any of the preceding aspects, further comprising determining the zone membership in response to a triggering event.

[0130] Aspect 8: The method according to any one of the preceding aspects, further comprising: selecting a second federated learning model for inference based on the zone membership.

[0131] Aspect 9: According to the method described in any one of the preceding aspects, the method further includes: storing the joint learning data by the UE when switching from a first joint learning area to a second joint learning area, the switching occurring without network service; and uploading the joint learning data to the joint learning area manager after the network service is restored.

[0132] Aspect 10: A device comprising: a memory; and at least one processor, the at least one processor coupled to the memory, the at least one processor configured to: receive a zone determination function based on registering a joint learning process for training a first joint learning model; determine zone membership based on UE parameters and the zone determination function; select the first joint learning model based on the zone membership; and train the first joint learning model.

[0133] Aspect 11: The apparatus according to aspect 10, wherein the at least one processor is further configured to: tabulate training data based on the zone membership; and communicate with a federated learning zone manager corresponding to the zone membership.

[0134] Aspect 12: The apparatus according to aspect 10 or 11, wherein the at least one processor is further configured to: receive an updated zone determination function from a zone partitioning maintainer.

[0135] Aspect 13: The apparatus according to any one of Aspects 10 to 12, wherein the at least one processor is further configured to: receive an updated zone topology map from a zone partition retainer, the updated zone topology map indicating an updated joint learning zone manager for each zone.

[0136] Aspect 14: The apparatus according to any one of aspects 10 to 13, wherein the at least one processor is further configured to periodically determine the zone membership.

[0137] Aspect 15: An apparatus according to any one of Aspects 10 to 14, wherein the at least one processor is further configured to: store sensor data associated with parameters; and determine data samples for training regarding a specific area based on the parameters associated with the sensor data.

[0138] Aspect 16: The apparatus according to any one of aspects 10 to 15, wherein the at least one processor is further configured to determine the zone membership in response to a triggering event.

[0139] Aspect 17: The apparatus according to any one of aspects 10 to 16, wherein the at least one processor is further configured to select a second federated learning model for inference based on the zone membership.

[0140] Aspect 18: An apparatus according to any one of Aspects 10 to 17, wherein the at least one processor is further configured to: store the joint learning data when switching from a first joint learning area to a second joint learning area, the switching occurring in the absence of network service; and upload the joint learning data to the joint learning area manager after the network service is restored.

[0141] Aspect 19: A device comprising: a component for receiving a zone determination function by a user equipment (UE) based on registering a joint learning process for training a first joint learning model; a component for determining zone membership by the UE based on UE parameters and the zone determination function; a component for selecting the first joint learning model by the UE based on the zone membership; and a component for training the first joint learning model by the UE.

[0142] Aspect 20: The apparatus according to aspect 19, further comprising: a component for tabulating training data based on the zone membership; and a component for communicating with a federated learning zone manager corresponding to the zone membership.

[0143] Aspect 21: The apparatus according to aspect 19 or 20, further comprising: a means for receiving an updated zone determination function from a zone partitioning maintainer.

[0144] Aspect 22: The apparatus according to any one of Aspects 19 to 21, further comprising: a component for receiving an updated zone topology map from a zone partition retainer, wherein the updated zone topology map indicates an updated joint learning zone manager for each zone.

[0145] Aspect 23: The apparatus according to any one of aspects 19 to 22, further comprising means for periodically determining the zone membership.

[0146] Aspect 24: An apparatus according to any one of Aspects 19 to 23, the apparatus further comprising: a component for storing sensor data associated with parameters; and a component for determining data samples for training about a specific area based on the parameters associated with the sensor data.

[0147] Aspect 25: The apparatus according to any one of aspects 19 to 24, further comprising: means for determining the zone membership in response to a triggering event.

[0148] Aspect 26: The apparatus according to any one of aspects 19 to 25, further comprising: a component for selecting a second joint learning model for inference based on the zone membership.

[0149] Aspect 27: An apparatus according to any one of Aspects 19 to 26, the apparatus further comprising: a component for storing joint learning data by the UE when switching from a first joint learning area to a second joint learning area, the switching occurring without network service; and a component for uploading the joint learning data to the joint learning area manager after restoring network service.

[0150] Aspect 28: A non-transitory computer-readable medium having program code recorded thereon, the program code being executed by a processor and comprising: program code for receiving, by a user equipment (UE), a zone determination function based on registering a joint learning process for training a first joint learning model; program code for determining, by the UE, zone membership based on UE parameters and the zone determination function; program code for selecting, by the UE, the first joint learning model based on the zone membership; and program code for training the first joint learning model by the UE.

[0151] Aspect 29: The non-transitory computer-readable medium of aspect 28, wherein the program code further comprises: program code for tabulating training data based on the zone membership; and program code for communicating with a federated learning zone manager corresponding to the zone membership.

[0152] Aspect 30: The non-transitory computer readable medium of aspect 28 or 29, wherein the program code further comprises: program code for receiving an updated zone determination function from a zone partition maintainer.

[0153] Aspect 31: A non-transitory computer-readable medium according to any one of Aspects 28 to 30, wherein the program code further comprises: program code for receiving an updated zone topology map from a zone partitioning retainer, the updated zone topology map indicating an updated federated learning zone manager for each zone.

[0154] Aspect 32: The non-transitory computer readable medium of any one of aspects 28 to 31, wherein the program code further comprises program code for periodically determining the zone membership.

[0155] Aspect 33: A non-transitory computer-readable medium according to any one of Aspects 28 to 32, wherein the program code also includes program code for storing sensor data associated with parameters; and program code for determining data samples for training regarding a specific area based on the parameters associated with the sensor data.

[0156] Aspect 34: The non-transitory computer readable medium of any one of aspects 28 to 33, wherein the program code further comprises program code for determining the zone membership in response to a triggering event.

[0157] Aspect 35: The non-transitory computer readable medium of any one of Aspects 28 to 34, wherein the program code further comprises program code for selecting a second federated learning model for inference based on the region membership.

[0158] Aspect 36: A non-transitory computer-readable medium according to any one of Aspects 28 to 35, wherein the program code also includes: program code for storing joint learning data by the UE when switching from a first joint learning area to a second joint learning area, the switching occurring without network service; and program code for uploading the joint learning data to the joint learning area manager after restoring network service.

[0159] The foregoing disclosure provides illustration and description, but is not intended to be exhaustive or to limit the aspects to the precise forms disclosed. Modifications and variations may be made in light of the above disclosure or may be acquired from practice of these aspects.

[0160] As used, the term "component" is intended to be broadly interpreted as hardware, firmware, and / or a combination of hardware and software. As used, a processor is implemented using hardware, firmware, and / or a combination of hardware and software.

[0161] Some aspects are described in conjunction with thresholds. As used, satisfying a threshold may refer to a value being greater than a threshold, greater than or equal to a threshold, less than a threshold, less than or equal to a threshold, equal to a threshold, not equal to a threshold, etc., depending on the context.

[0162] It will be apparent that the described systems and / or methods can be implemented in various forms of hardware, firmware, and / or a combination of hardware and software. The actual dedicated control hardware or software code used to implement these systems and / or methods does not limit the aspects. Therefore, the operation and performance of these systems and / or methods are described without reference to specific software code, and it should be understood that software and hardware used to implement these systems and / or methods can be designed based at least in part on these descriptions.

[0163] Although specific combinations of features are set forth in the claims and / or disclosed in the specification, these combinations are not intended to limit the disclosure of various aspects. In fact, many of these features can be combined in a manner that is not specifically set forth in the claims and / or is not disclosed in the specification. Although each dependent claim listed below may directly rely on only one claim, the disclosure of various aspects includes each dependent claim combined with each other claim in the claim set. The phrase "at least one" mentioned in the list of items refers to any combination of those items, including a single member. As an example, "at least one of a, b or c" is intended to cover a, b, c, ab, ac, bc and abc, and any combination with multiple identical elements (e.g., aa, aaa, aab, aac, abb, acc, bb, bbb, bbc, cc and ccc, or any other ordering of a, b and c).

[0164] The elements, actions or instructions used should not be interpreted as critical or essential unless explicitly described as such. In addition, as used, the articles "a" and "an" are intended to include one or more items, and they can be used interchangeably with "one or more". In addition, as used, the terms "set" and "group" are intended to include one or more items (e.g., related items, unrelated items, combinations of related items and unrelated items, etc.), and can be used interchangeably with "one or more". If only one item is intended to be referred to, the phrase "only one" or similar terms will be used. In addition, as used, the terms "having" and the like are intended to be open terms. In addition, the phrase "based on" is intended to mean "based at least in part on", unless otherwise explicitly stated.

Claims

1. A processor-implemented method, the method comprising: receiving, by a user equipment (UE), a zone determination function based on a federated learning process registered for training a first federated learning model; determining, by the UE, zone membership based on UE parameters and the zone determination function; selecting, by the UE, the first federated learning model based on the zone membership; as well as The first joint learning model is trained by the UE.

2. The method according to claim 1, further comprising: tabulating training data based on the zone membership; as well as Communicating with a federated learning zone manager corresponding to the zone membership.

3. The method according to claim 1, further comprising: A zone determination function receives updates from a zone partition maintainer.

4. The method according to claim 1, further comprising: An updated zone topology map is received from the zone partition maintainer, the updated zone topology map indicating an updated federated learning zone manager for each zone.

5. The method of claim 1, further comprising periodically determining the zone membership.

6. The method according to claim 1, further comprising: storing sensor data associated with the parameters; as well as Based on the parameters associated with the sensor data, data samples for training with respect to a particular zone are determined.

7. The method of claim 1, further comprising determining the zone membership in response to a triggering event.

8. The method according to claim 1, further comprising: A second federated learning model is selected for inference based on the zone membership.

9. The method according to claim 1, further comprising: storing the joint learning data by the UE when switching from the first joint learning area to the second joint learning area, the switching occurring without network service; as well as After the network service is restored, the joint learning data is uploaded to the joint learning zone manager.

10. A device, comprising: Memory; and at least one processor, the at least one processor coupled to the memory, the at least one processor configured to: receiving a region determination function based on a federated learning process registered for training a first federated learning model; determining zone membership based on the parameters and the zone determination function; selecting the first federated learning model based on the zone membership; as well as The first joint learning model is trained.

11. The apparatus of claim 10, wherein the at least one processor is further configured to: tabulating training data based on the zone membership; and Communicating with a federated learning zone manager corresponding to the zone membership.

12. The apparatus of claim 10, wherein the at least one processor is further configured to receive an updated zone determination function from a zone partitioning maintainer.

13. The apparatus of claim 10, wherein the at least one processor is further configured to: receive an updated zone topology map from a zone partition maintainer, the updated zone topology map indicating an updated federated learning zone manager for each zone.

14. The apparatus of claim 10, wherein the at least one processor is further configured to periodically determine the zone membership.

15. The apparatus of claim 10, wherein the at least one processor is further configured to: storing sensor data associated with the parameters; and Based on the parameters associated with the sensor data, data samples for training with respect to a particular zone are determined.

16. The apparatus of claim 10, wherein the at least one processor is further configured to determine the zone membership in response to a triggering event.

17. The apparatus of claim 10, wherein the at least one processor is further configured to select a second federated learning model for inference based on the zone membership.

18. The apparatus of claim 10, wherein the at least one processor is further configured to: storing the federated learning data when switching from a first federated learning region to a second federated learning region, the switching occurring without network service; and After the network service is restored, the joint learning data is uploaded to the joint learning zone manager.

19. A device, comprising: means for receiving, by a user equipment (UE), a zone determination function based on registering a federated learning process for training a first federated learning model; means for determining, by the UE, zone membership based on UE parameters and the zone determination function; means for selecting, by the UE, the first federated learning model based on the zone membership; and A component for training the first joint learning model by the UE.

20. The apparatus according to claim 19, further comprising: means for tabulating training data based on said zone membership; and Means for communicating with a federated learning zone manager corresponding to said zone membership.

21. The apparatus according to claim 19, further comprising: Means for receiving updated zone determination functionality from a zone partition maintainer.

22. The apparatus according to claim 19, further comprising: Means for receiving an updated zone topology map from a zone partition maintainer, the updated zone topology map indicating an updated federated learning zone manager for each zone.

23. The apparatus of claim 19, further comprising means for periodically determining the zone membership.

24. The apparatus according to claim 19, further comprising: means for storing sensor data associated with the parameters; and Means for determining data samples for training with respect to a particular zone based on the parameters associated with the sensor data.

25. The apparatus of claim 19, further comprising means for determining the zone membership in response to a triggering event.

26. The apparatus of claim 19, further comprising means for selecting a second federated learning model for inference based on the zone membership.

27. The apparatus according to claim 19, further comprising: means for storing, by the UE, joint learning data when switching from a first joint learning area to a second joint learning area, the switching occurring without network service; and A component for uploading the federated learning data to the federated learning zone manager after the network service is restored.

28. A non-transitory computer readable medium having program code recorded thereon, the program code being executed by a processor and comprising: program code for receiving, by a user equipment (UE), a zone determination function based on registering a federated learning process for training a first federated learning model; program code for determining, by the UE, zone membership based on UE parameters and the zone determination function; program code for selecting, by the UE, the first federated learning model based on the zone membership; and Program code for training the first joint learning model by the UE.

29. The non-transitory computer readable medium of claim 28, wherein the program code further comprises: program code for tabulating training data based on the zone membership; and Program code for communicating with a federated learning zone manager corresponding to the zone membership.

30. The non-transitory computer readable medium of claim 28, wherein the program code further comprises: Program code for a zone determination function that receives updates from a zone partition maintainer.

Images