Machine learning component update reporting in federated learning

Abstract

Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a client device can receive a reporting configuration that indicates one or more reporting conditions, where the reporting configuration further indicates that, based at least in part on the one or more reporting conditions being satisfied, the client device is to report an update associated with a machine learning component. The client device can transmit, to a server device, the update associated with the machine learning component based at least in part on whether the one or more reporting conditions are satisfied. Numerous other aspects are provided.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This Patent Application claims priority to U.S. Provisional Patent Application No. 63 / 198,048, filed September 25, 2020, entitled “MACHINE LEARNING COMPONENT UPDATE REPORTING IN FEDERATED LEARNING,” and U.S. Nonprovisional Patent Application No. 17 / 448,653, filed September 23, 2021, entitled “MACHINE LEARNING COMPONENT UPDATE REPORTING IN FEDERATED LEARNING,” the entire contents of both of these applications are hereby expressly incorporated by reference herein in their entirety. TECHNICAL FIELD

[0003] Aspects of the disclosure relate generally to wireless communication, and to techniques and apparatuses for machine learning component update reporting in federated learning. BACKGROUND

[0004] Wireless communication systems are widely deployed to provide various telecommunication services such as telephony, video, data, messaging, and broadcasts. Typical wireless communication systems can employ multiple-access technologies capable of supporting 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 promulgated by the Third Generation Partnership Project (3 GPP).

[0005] A wireless network can include a number of base stations (BSs) that can support communication for a number of user equipment (UEs). A UE can communicate with a BS via the downlink and uplink. “Downlink” (or forward link) refers to the communication from the BS to the UE, and “uplink” (or reverse link) refers to the communication from the UE to the BS. As will be described in more detail

[0006] The above multiple access technologies have been adopted in various telecommunication standards to provide common protocol that enables different wireless devices to communicate on a municipal, national, regional, and even global level. NR, which can also be referred to as 5G, is a set of enhancements to the LTE mobile standard promulgated by 3GPP. NR is designed to better support mobile broadband Internet access by improving spectral efficiency, lowering costs, improving services, making use of new spectrum, and better integrating with other open standards using orthogonal frequency division multiplexing (OFDM) with a cyclic prefix (CP) (CP-OFDM) on the downlink (DL), using CP- OFDM and / or SC-FDM (e.g., also known as discrete Fourier transform spread orthogonal frequency division multiplexing (DFT-s-OFDM)) on the uplink (UL), as well as supporting beamforming, multiple-input multiple-output (MIMO) antenna technology, and carrier aggregation. However, as the demand for mobile broadband access continues to increase, there exists a need for further improvements in LTE and NR technologies. Preferably, these improvements should be applicable to other multiple access technologies and the telecommunication standards that employ these technologies. SUMMARY

[0007] Aspects generally include a method of wireless communication performed by a client device, the method including receiving a reporting configuration indicating one or more reporting conditions, wherein the reporting configuration further indicates that, based at least in part on the one or more reporting conditions being satisfied, the client device is to report an update associated with a machine learning component, and transmitting, to a server device, the update associated with the machine learning component based at least in part on whether the one or more reporting conditions are satisfied.

[0008] In some aspects, a method of wireless communication performed by a server device includes transmitting, to a client device, a reporting configuration indicating one or more reporting conditions, wherein the reporting configuration further indicates that, based at least in part on the one or more reporting conditions being satisfied, the client device is to report an update associated with a machine learning component, and receiving, from the client device, the update associated with the machine learning component based at least in part on whether the one or more reporting conditions are satisfied.

[0009] In some aspects, a client device for wireless communication includes a memory; and one or more processors coupled to the memory, the memory and the one or more processors configured to receive a reporting configuration indicating one or more reporting conditions, wherein the reporting configuration further indicates that, based at least in part on the one or more reporting conditions being satisfied, the client device is to report an update associated with a machine learning component, and transmit, to a server device, the update associated with the machine learning component based at least in part on whether the one or more reporting conditions are satisfied.

[0010] In some aspects, a server device for wireless communication includes a memory; and one or more processors coupled to the memory, the memory and the one or more processors configured to transmit, to a client device, a reporting configuration that indicates one or more reporting conditions, wherein the reporting configuration further indicates that, based at least in part on the one or more reporting conditions being satisfied, the client device is to report an update associated with a machine learning component; and receive, from the client device, the update associated with the machine learning component based at least in part on whether the one or more reporting conditions are satisfied.

[0011] In some aspects, a non-transitory computer-readable medium storing a set of instructions for wireless communication includes instructions to cause a client device, when executed by one or more processors of the client device, to receive a reporting configuration that indicates one or more reporting conditions, wherein the reporting configuration further indicates that, based at least in part on the one or more reporting conditions being satisfied, the client device is to report an update associated with a machine learning component; and transmit, to a server device, the update associated with the machine learning component based at least in part on whether the one or more reporting conditions are satisfied.

[0012] In some aspects, a non-transitory computer-readable medium storing a set of instructions for wireless communication includes instructions to cause a server device, when executed by one or more processors of the server device, to transmit, to a client device, a reporting configuration that indicates one or more reporting conditions, wherein the reporting configuration further indicates that, based at least in part on the one or more reporting conditions being satisfied, the client device is to report an update associated with a machine learning component; and receive, from the client device, the update associated with the machine learning component based at least in part on whether the one or more reporting conditions are satisfied.

[0013] In some aspects, an apparatus for wireless communication includes means for receiving a reporting configuration that indicates one or more reporting conditions, wherein the reporting configuration further indicates that, based at least in part on the one or more reporting conditions being satisfied, the apparatus is to report an update associated with a machine learning component; and means for transmitting, to a server device, the update associated with the machine learning component based at least in part on whether the one or more reporting conditions are satisfied.

[0014] In some aspects, an apparatus for wireless communication includes means for transmitting, to a client device, a reporting configuration that indicates one or more reporting conditions, wherein the reporting configuration further indicates that, based at least in part on the one or more reporting conditions being satisfied, the client device is to report an update associated with a machine learning component; and means for receiving, from the client device, the update associated with the machine learning component based at least in part on whether the one or more reporting conditions are satisfied.

[0015] In some aspects, the methods, apparatuses, devices, systems, computer program products, non-transitory computer-readable media, user equipment, base stations, nodes, wireless communication devices, client devices, and / or processing systems, as substantially described herein and as illustrated by the appropriate dependent claims and the following figures and description.

[0016] The foregoing has outlined rather broadly the features and technical advantages of examples according to the disclosure in order that the detailed description that follows can be better understood. Additional features and advantages will be described hereinafter. The disclosed concepts and specific examples can be readily utilized as bases for the design of other structures for carrying out the same purposes of the present disclosure. Such equivalent constructions do not depart from the spirit and scope of the appended claims. The characteristics of the concepts disclosed herein, both their organization and method of operation, together with associated advantages will be better understood from the following description when considered in connection with the accompanying figures. Each of the figures is provided for the purpose of illustration and description, and is not intended as a limitation on the claims. BRIEF DESCRIPTION OF DRAWINGS

[0017] So that the above-recited features of the present disclosure can be understood in detail, a more particular description, briefly summarized above, can be had by reference to various aspects, some of which are illustrated in the appended drawings. It is to be noted, however, that the appended drawings illustrate only certain typical aspects of this disclosure and are therefore not to be considered limiting of its scope, for the description can admit to other equally effective aspects. Like reference numerals in the various drawings can designate the same or similar elements.

[0018] Figure 1 is a diagram illustrating an example of a wireless network, in accordance with the present disclosure.

[0019] Figure 2 is a diagram illustrating an example of a base station in communication with a user equipment (UE) in a wireless network, in accordance with the present disclosure.

[0020] Figure 3 and Figure 4 is a diagram illustrating an example associated with machine learning component update reporting in federated learning, in accordance with the present disclosure.

[0021] Figure 5 and Figure 6 is a diagram illustrating an example process associated with machine learning component update reporting in federated learning, in accordance with the present disclosure.

[0022] Figures 7-10 is a block diagram of an example apparatus for wireless communication, in accordance with the present disclosure. DETAILED DESCRIPTION

[0023] Aspects of the disclosure are described more fully below with reference to the accompanying drawings. This disclosure may, however, be embodied in many different forms and should not be construed as limited to any specific structure or function presented throughout this disclosure. Rather, these aspects are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art. Based on the teachings herein, one skilled in the art should appreciate that the scope of the disclosure is intended to cover any aspect of the disclosure disclosed herein, whether implemented independently of, or combined with, any other aspect of the disclosure. For example, an apparatus can be implemented or a method can be practiced using any number of the aspects set forth herein. In addition, the scope of the disclosure is intended to cover such an apparatus or method which can be practiced using other structure, functionality, or structure and functionality in addition to or other than the various aspects of the disclosure set forth herein. It should be understood that any aspect of the disclosure disclosed herein can be embodied by one or more elements of a claim.

[0024] Several aspects of telecommunication systems will now be presented with reference to various apparatus and methods. These apparatus and methods 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 combinations thereof. Whether such elements are implemented as hardware or software depends on the particular application and design constraints imposed on the overall system.

[0025] Various aspects can include one or more client devices that can communicate with one or more server devices. A client device can include software and / or hardware configured to perform one or more operations and communicate with one or more server devices. A server device can include software and / or hardware configured to perform one or more operations and communicate with one or more client devices. A client device and / or a server device can be, include, be included in, and / or be implemented as any number of different types of computing devices, such as, for example, network devices (e.g., wireless network devices and / or wired network devices), portable computers, laptop computers, tablet devices, workstations, personal computers, controllers, vehicle-mounted control networks, Internet of Things (IoT) devices, traffic control devices, Integrated Access and Backhaul (IAB) nodes, user equipment (UE), base stations, relay stations, switches, routers, customer premises equipment (CPE), and / or vehicles (e.g., land-based vehicles, aircraft, non-ground-based vehicles, and / or water-based vehicles).

[0026] As described above, in some aspects, client devices and / or server devices can be, include, be included in, and / or be implemented on one or more wireless network devices. For example, in some aspects, a client device can be, include, be included in, and / or be implemented on a UE, and a server device can be, include, be included in, and / or be implemented on a base station. In some aspects, a client device can include a server device configured to operate as a client. In some aspects, a server device can include a client device configured to operate as a server. In some aspects, one or more server devices and / or one or more client devices can communicate using any number of types of communication connections, such as, for example, a wired network, a wireless network, a multihop network, and / or a combination of wired network(s), wireless network(s), and / or multihop network(s).

[0027] Figure 1 and Figure 2 The following detailed description of implementations refers to the accompanying drawings, which form a part of this application. The drawings show, by way of illustration, various implementations in which one or more of the aspects can be employed. Figures 3-6 The following detailed description of implementations refers to the accompanying drawings, which form a part of this application. The drawings show, by way of illustration, various implementations in which one or more of the aspects can be employed. Figure 1 and Figure 2 The following detailed description of implementations refers to the accompanying drawings, which form a part of this application. The drawings show, by way of illustration, various implementations in which one or more of the aspects can be employed. Figure 1 and Figure 2 The following detailed description of implementations refers to the accompanying drawings, which form a part of this application. The drawings show, by way of illustration, various implementations in which one or more of the aspects can be employed. Figures 7-10 The following detailed description of implementations refers to the accompanying drawings, which form a part of this application. The drawings show, by way of illustration, various implementations in which one or more of the aspects can be employed.

[0028] It should be noted that while aspects can be described herein using terminology commonly associated with a 5G or NR radio access technology (RAT), aspects of the present disclosure can be applied to other RATs, such as a 3G RAT, a 4G RAT, and / or a RAT subsequent to 5G (e.g., 6G).

[0029] Figure 1 is a diagram illustrating an example of a wireless network 100, in accordance with the present disclosure. As described above, one or more aspects of the wireless network 100 can be used to implement, among other things, a UE and / or a base station as described in Figure 3Aspects of one or more clients and servers described in this specification and in the accompanying drawings can be implemented as communication software using an operating system such as the Windows® operating system (OS) available from the Microsoft Corporation, Mac OS X® available from Apple Inc., and others. The wireless network 100 can be or include elements of a 5G (NR) network and / or an LTE network, among other examples. The wireless network 100 can include a number of base stations 110 (shown as BS 110a, BS 110b, BS 110c, and BS 1 lOd) and other network entities. A base station (BS) is an entity that communicates with user equipment (UEs) and can also be referred to as an NR BS, a NodeB, a gNB, a 5G nodeB (NB), an access point, a transmit receive point (TRP), and / or the like. Each BS can provide communication coverage for a particular geographic area. In 3GPP, the term“cell” can refer to a coverage area of a BS and / or a BS subsystem serving the coverage area, depending on the context in which the term is used. In some aspects, a BS can be referred to as a server (such as the server device 308 shown in Figure 3 and described below). A UE can be, include, be included in, and / or be Figure 3 implemented as a client (such as the client device 302 shown in and described below). In some aspects, a BS can be, include, be included in, and / or be implemented as a client. In some aspects, a UE can be, include, be included in, and / or be implemented as a server.

[0030] A BS can be a macro BS, a pico BS, a femto BS, and / or another type of BS. A macro BS can cover a relatively large geographic area (e.g., several kilometers in radius) and can allow restricted access by UEs having subscription plans with a network operator providing the macro cell. A pico BS can cover a relatively small geographic area and can allow restricted access by UEs having subscription plans with a network operator providing the pico cell. A femto BS can cover a relatively small geographic area (e.g., a home) and can allow restricted access by UEs having subscription plans with a network operator providing the femto cell, or restricted access by UEs in a closed subscriber group. A BS for a macro cell can be referred to as a macro BS. A BS for a pico cell can be referred to as a pico BS. A BS for a femto cell can be referred to as a femto BS or a home BS. In Figure 1 the example shown in FIG. 1, the BS 110a can be a macro BS for a macro cell 102a, the BS 110b can be a pico BS for a pico cell 102b, and the BS 110c can be a femto BS for a femto cell 102c. A BS can support one or multiple (e.g., three) cells. The terms“eNB,”“base station,”“NR BS,”“gNB,”“TRP,”“AP,”“Node B,”“5G NB,” and“cell” can be used interchangeably.

[0031] In some examples, a cell is not necessarily stationary, and the geographic area of the cell can move according to the location of a mobile BS. In some examples, the BSs can be interconnected to one another 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 a direct physical connection or a virtual network, using any appropriate transport network.

[0032] Wireless network 100 can also include relay stations. A relay station is an entity that can receive a transmission of data from an upstream station (e.g., a BS or a UE) and send a transmission of the data to a downstream station (e.g., a UE or a BS). A relay station can also be a UE that can relay transmissions for other UEs. Figure 1 In the example shown in Figure 1, a relay BS 1 lOd can communicate with macro BS 110a and a UE 120d in order to facilitate communication between BS 110a and UE 120d. A relay BS can also be referred to as a relay station, a relay base station, a repeater, etc.

[0033] In some aspects, wireless network 100 can include one or more non-terrestrial network (NTN) deployments in which non-terrestrial wireless communication devices can include UEs (interchangeably referred to herein as “non-terrestrial UEs”), BSs (interchangeably referred to herein as “non-terrestrial BSs” and “non-terrestrial base stations”), relay stations (interchangeably referred to herein as “non-terrestrial relay stations”), etc. As used herein, an “NTN” can refer to a network for which access is facilitated by non-terrestrial UEs, non-terrestrial BSs, non-terrestrial relay stations, etc.

[0034] Wireless network 100 can include any number of non-terrestrial wireless communication devices. The non-terrestrial wireless communication devices can include satellites, manned aircraft systems, unmanned aircraft systems (UAS) platforms, etc. The satellites can include low earth orbit (LEO) satellites, medium earth orbit (MEO) satellites, geostationary earth orbit (GEO) satellites, high elliptical orbit (HEO) satellites, etc. The manned aircraft systems can include airplanes, helicopters, dirigibles, etc. The UAS platforms can include high-altitude platform stations (HAPS), and can include balloons, dirigibles, airplanes, etc. The non-terrestrial wireless communication devices can be part of an NTN that is separate from wireless network 100. Alternatively, the NTN can be part of wireless network 100. The satellites can communicate directly and / or indirectly with other entities in wireless network 100 using satellite communications. The other entities can include UEs (e.g., terrestrial UEs and / or non-terrestrial UEs), other satellites in one or more NTN deployments, other types of BSs (e.g., stationary and / or ground-based BSs), relay stations, one or more components and / or devices included in a core network of wireless network 100, etc.

[0035] Wireless network 100 can be a heterogeneous network that includes BSs of different types, such as macro BSs, pico BSs, femto BSs, relay BSs, or the like. These different types of BSs can have different transmit power levels, different coverage areas, and different impacts on interference. For example, macro BSs can have a high transmit power level (e.g., 5 to 40 Watts), whereas pico BSs, femto BSs, and relay BSs can have lower transmit power levels (e.g., 0.1 to 2 Watts).

[0036] A network controller 130 can couple to a set of BSs and can provide coordination and control for these BSs. Network controller 130 can communicate with the BSs via a backhaul. The BSs can also communicate with one another, e.g., directly or indirectly via a wireless or wireline backhaul. For example, in some aspects, wireless network 100 can be, include, or be included within a wireless backhaul network (sometimes referred to as an integrated access and backhaul (IAB) network). In an IAB network, at least one base station (e.g., base station 110) can be an anchor base station that communicates with a core network via a wireline backhaul link (such as a fiber connection). The anchor base station can also be referred to as an IAB donor (or IAB-donor), a central entity, a central unit, or the like. The IAB network can include one or more non-anchor base stations, sometimes referred to as relay base stations, IAB nodes (or IAB-nodes). The non-anchor base stations can communicate directly or indirectly with the anchor base station (e.g., via one or more non-anchor base stations) via one or more backhaul links to form a backhaul path to the core network for carrying backhaul traffic. The backhaul links can be wireless links. The anchor base station and / or the non-anchor base stations can communicate with one or more UEs (e.g., UE 120) via access links, which can be wireless links for carrying access traffic.

[0037] In some aspects, a radio access network including an IAB network can utilize millimeter wave technology and / or directional communications (e.g., beamforming, precoding, or the like) for communications between base stations and / or UEs (e.g., between two base stations, between two UEs, and / or between a base station and a UE). For example, a wireless backhaul link between base stations can use millimeter waves to carry information and / or can use beamforming, precoding, or the like to be directed toward a target base station. Similarly, a wireless access link between a UE and a base station can use millimeter waves and / or can be directed toward a target wireless node (e.g., a UE and / or a base station). In this way, inter-link interference can be reduced.

[0038] The UEs 120 (e.g., 120a, 120b, 120c) can be dispersed throughout the wireless network 100, and each UE can be stationary or mobile. A UE can also be referred to as an access terminal, a terminal, a mobile station, a subscriber unit, a station, etc. A UE can 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, a camera, a gaming device, a netbook, a smartbook, an ultrabook, a medical device or equipment, biometric sensors / devices, wearable devices (smart watches, smart clothing, smart glasses, smart wrist bands, smart jewelry (e.g., smart ring, smart bracelet)), an entertainment device (e.g., a music or video device, or a satellite radio), a vehicular component or sensor, smart meters / sensors, industrial manufacturing equipment, a global positioning system device, or any other suitable device that is configured to communicate via a wireless or wired medium.

[0039] Some UEs can be considered machine-type communication (MTC) or evolved or enhanced machine-type communication (eMTC) UEs. MTC and eMTC UEs include, for example, robots, drones, remote devices, sensors, meters, monitors, and / or location tags, that can communicate with a base station, another device (e.g., remote device), or some other entity. A wireless node can provide, for example, connectivity for or to a network (e.g., a wide area network such as Internet or a cellular network) via a wired or wireless communication link. Some UEs can be considered Intemet-of-Things (IoT) devices, and / or can implement NB-IoT (narrowband

[0040] In general, any number of wireless networks can be deployed in a given geographic area. Each wireless network can support a particular RAT and can operate on one or more frequencies. A RAT can also be referred to as a radio technology, an air interface, etc. A frequency can also be referred to as a carrier, a frequency channel, etc. Each frequency can support a single RAT in a given geographic area in order to avoid interference between wireless networks of different RATs. In some cases, NR or 5G RAT networks can be deployed.

[0041] In some aspects, two or more UEs 120 (e.g., shown as UE 120a and UE 120e) may communicate directly using one or more sidelink channels (e.g., without using base station 110 as an intermediary device). For example, UEs 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 or vehicle-to-infrastructure (V2I) protocols) and / or mesh networks. In some aspects, UEs 120 may perform scheduling operations, resource selection operations, and / or other operations as described elsewhere herein, as performed by base station 110.

[0042] Devices in the wireless network 100 can communicate using the electromagnetic spectrum, which can be subdivided into various categories, bands, channels, etc., based on frequency or wavelength. For example, devices in the wireless network 100 can communicate using an operating band with a first frequency range (FR1), which can span from 410 MHz to 7.125 GHz, and / or can communicate using an operating band with a second frequency range (FR2), which can span from 24.25 GHz to 52.6 GHz. Frequencies between FR1 and FR2 are generally referred to as mid-band frequencies. Although a portion of FR1 is greater than 6 GHz, FR1 is often referred to as the "below 6 GHz" band. Similarly, FR2 is often referred to as the "millimeter wave" band, although it differs from the Extremely High Frequency (EHF) band (30 GHz–300 GHz) recognized as a "millimeter wave" band by the International Telecommunication Union (ITU). Therefore, unless otherwise expressly stated, it should be understood that the terms "below 6 GHz" and the like (if used herein) can broadly refer to frequencies below 6 GHz, frequencies within FR1, and / or mid-band frequencies (e.g., above 7.125 GHz). Similarly, unless otherwise expressly stated, it should be understood that the terms "millimeter wave" and the like (if used herein) can broadly refer to frequencies within the EHF band, frequencies within FR2, and / or mid-band frequencies (e.g., below 24.25 GHz). It is contemplated that the frequencies included in FR1 and FR2 can be modified, and the techniques described herein can be applied to these modified frequency ranges.

[0043] like Figure 1As shown, UE 120 can include first communication manager 140. As described in more detail elsewhere herein, first communication manager 140 can receive a reporting configuration that indicates one or more reporting conditions, where the reporting configuration further indicates that, based at least in part on the one or more reporting conditions being satisfied, the client device is to report an update associated with a machine learning component and, based at least in part on whether the one or more reporting conditions are satisfied, transmit the update associated with the machine learning component to a server device. Additionally, or alternatively, first communication manager 140 can perform one or more other operations described herein.

[0044] In some aspects, base station 110 can include second communication manager 150. As described in more detail elsewhere herein, second communication manager 150 can transmit, to a client device, a reporting configuration that indicates one or more reporting conditions, where the reporting configuration further indicates that, based at least in part on the one or more reporting conditions being satisfied, the client device is to report an update associated with a machine learning component and, based at least in part on whether the one or more reporting conditions are satisfied, receive the update associated with the machine learning component from the client device. Additionally, or alternatively, second communication manager 150 can perform one or more other operations described herein.

[0045] As indicated above, Figure 1 are provided merely for purposes of example. Other examples can differ from what is described Figure 1 in connection with the examples described with reference to

[0046] Figure 2 is a schematic illustration of an example 200 in which a base station 110 of a wireless network 100 communicates with a UE 120 in accordance with this disclosure. A base station 110 can be equipped with T antennas 234a through 234t, and a UE 120 can be equipped with R antennas 252a through 252r, where in general T > 1 and R > 1.

[0047] At base station 110, a transmit processor 220 can receive data from a data source 212 for one or more UEs, select one or more modulation and coding schemes (MCS) for each UE based at least in part on channel quality indicators (CQIs) received from the UE, process (e.g., encode and modulate) the data for each UE based at least in part on the MCS selected for the UE, and provide data symbols for all UEs. Transmit processor 220 can also process system information (e.g., for semi-static resource partitioning information (SRPI)) and control information (e.g., CQI requests, grants, and / or upper layer signaling) and provide overhead symbols and control symbols. Transmit processor 220 can also generate reference symbols for reference signals (e.g., a cell-specific reference signal (CRS) or a demodulation reference signal (DMRS)) and synchronization signals (e.g., a primary synchronization signal (PSS) or a secondary synchronization signal (SSS)). A transmit (TX) multiple-input multiple-output (MIMO) processor 230 can perform spatial processing (e.g., precoding) on the data symbols, the control symbols, the overhead symbols, and / or the reference symbols, if applicable, and provide T output symbol streams to T modulators (MODs) 232a through 232t. Each modulator 232 can process a respective output symbol stream (e.g., for OFDM) to obtain an output sample stream. Each modulator 232 can further process (e.g., convert to analog, amplify, filter, and upconvert) the output sample stream to obtain a downlink signal. T downlink signals from modulators 232a through 232t can be transmitted via T antennas 234a through 234t, respectively.

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

[0049] The network controller 130 can include a communication unit 294, a controller / processor 290, and a memory 292. The network controller 130 can include, for example, one or more devices in a core network. The network controller 130 can communicate with the base station 110 via the communication unit 294.

[0050] Antennas (e.g., antennas 234a-234t and / or antennas 252a-252r) can include or can be included within one or more antenna panels, antenna groups, antenna element groups, and / or antenna arrays, among other examples. An antenna panel, antenna group, antenna element group, and / or antenna array can include one or more antenna elements. An antenna panel, antenna group, antenna element group, and / or antenna array can include a set of co-planar antenna elements and / or a set of non-co-planar antenna elements. An antenna panel, antenna group, antenna element group, and / or antenna array can include antenna elements within a single housing and / or antenna elements within multiple housings. An antenna panel, antenna group, antenna element group, and / or antenna array can include one or more antenna elements coupled to one or more transmit and / or receive components, such as Figure 2 one or more components of the UE 120.

[0051] On the uplink, at UE 120, a transmit processor 264 can receive and process data from a data source 262 and control information (e.g., for reports comprising RSRP, RSSI, RSRQ, and / or CQI) from controller / processor 280. Transmit processor 264 can also generate reference symbols for one or more reference signals. The symbols from transmit processor 264 can be precoded by a TX MIMO processor 266 if applicable, further processed by modulators 254a through 254r (e.g., for DFT-s-OFDM or CP-OFDM), and transmitted to base station 110. In some aspects, a modulator and a demodulator (e.g., MOD / DEMOD 254) of the UE 120 can be included in a modem of the UE 120. In some aspects, the UE 120 includes a transceiver. The transceiver can include any combination of antennas 252, modulators and / or demodulators 254, MIMO detector 256, receive processor 258, transmit processor 264, and / or TX MIMO processor 266. The transceiver can be used by a processor (e.g., controller / processor 280) and memory 282 to perform any of the methods described herein.

[0052] At base station 110, the uplink signals from UE 120 and other UEs can be received by antennas 234, processed by demodulators 232, detected by a MIMO detector 236 if applicable, and further processed by a receive processor 238 to obtain decoded data and control information sent by UE 120. Receive processor 238 can provide the decoded data to a data sink 239 and to controller / processor 240 for control information. Base station 110 can include communication unit 244 and communicate to network controller 130 via communication unit 244. Base station 110 can include a scheduler 246 to schedule UEs 120 for downlink and / or uplink communications. In some aspects, a modulator and a demodulator (e.g., MOD / DEMOD 232) of the base station 110 can be included in a modem of the base station 110. In some aspects, the base station 110 includes a transceiver. The transceiver can include any combination of antennas 234, modulators and / or demodulators 232, MIMO detector 236, receive processor 238, transmit processor 220, and / or TX MIMO processor 230. The transceiver can be used by a processor (e.g., controller / processor 240) and memory 242 to perform any of the methods described herein.

[0053] Controller / processor 240 of base station 110, controller / processor 280 of UE 120, and / or Figure 2Any other components may perform one or more techniques associated with updating reports of machine learning components in federated learning, as described in more detail elsewhere in this document. For example, the controller / processor 240 of base station 110, the controller / processor 280 of UE 120, and / or Figure 2 Any other component can perform or direct, for example Figure 5 Process 500 Figure 6 The operation of process 600 and / or other processes as described herein. Memory 242 and memory 282 may store data and program code for base station 110 and UE 120, respectively. In some aspects, memory 242 and / or memory 282 may include a non-transitory computer-readable medium storing one or more instructions (e.g., code and / or program code) for wireless communication. For example, one or more instructions, when executed by one or more processors of base station 110 and / or UE 120 (e.g., directly or after compilation, translation, and / or interpretation), may cause one or more processors, UE 120, and / or base station 110 to perform or direct, for example... Figure 5 Process 500 Figure 6 The operation of process 600 and / or other processes as described herein. In some aspects, execution instructions may include run instructions, translation instructions, compilation instructions and / or interpretation instructions, and other examples.

[0054] In some aspects, a client (e.g., UE 120) may include a unit for receiving a reporting configuration indicating one or more reporting conditions, wherein the reporting configuration further indicates that: at least in part based on the satisfaction of one or more reporting conditions, the client device will report an update associated with the machine learning component, and / or a unit for sending an update associated with the machine learning component to a server device at least in part based on whether one or more reporting conditions are satisfied, and other examples. In some aspects, such a unit may include a combination of Figure 2 The UE 120 described includes one or more components such as controller / processor 280, transmit processor 264, TX MIMO processor 266, MOD 254, antenna 252, DEMOD 254, MIMO detector 256 and / or receive processor 258, and other examples.

[0055] In some aspects, a server (e.g., a base station 110) can include means for transmitting, to a client device, a reporting configuration indicating one or more reporting conditions, where the reporting configuration further indicates that, based at least in part on the one or more reporting conditions being satisfied, the client device is to report an update associated with a machine learning component, and / or means for receiving, from the client device, the update associated with the machine learning component based at least in part on whether the one or more reporting conditions are satisfied, among other examples. In some aspects, such means can include one or more components of base station 110 described in connection with FIG. 2, such as antenna 234, DEMOD 232, MIMO detector 236, receive processor 238, controller / processor 240, transmit processor 220, TX MIMO processor 230, MOD 232, and / or antenna 234, among other examples. Figure 2 One or more components of the base station 110 described, such as antenna 234, DEMOD 232, MIMO detector 236, receive processor 238, controller / processor 240, transmit processor 220, TX MIMO processor 230, MOD 232, and / or antenna 234, among other examples.

[0056] Although blocks in Figure 2 are shown as distinct components, the functionality described above with respect to blocks can be implemented in a single hardware, software, or combined component or in various combinations of components. For example, the functionality described with respect to transmit processor 264, receive processor 258, and / or TX MIMO processor 266 can be performed by controller / processor 280 or under the control of controller / processor 260.

[0057] As described above, Figure 2 are provided as examples. Other examples can differ from what is described with respect to examples described herein. Figure 2 described with respect to examples described herein.

[0058] A client device operating in a network can report information to a server device. The information can include information associated with received signals and / or positioning information, among other examples. For example, a client device can perform measurements associated with reference signals and report the measurements to a server device. In some examples, a client device can measure reference signals during a beam management procedure for channel state feedback (CSF), can measure received power of reference signals from a serving cell and / or neighboring cells, can measure signal strength between radio access technologies (e.g., WiFi) networks, and / or can measure sensor signals for detecting locations of one or more objects within an environment. However, reporting information to a server device can consume communication and / or network resources.

[0059] To reduce consumption of resources, a client device (e.g., a UE, a base station, a transmission reception point (TRP), a network device, a low earth orbit (LEO) satellite, a medium earth orbit (MEO) satellite, a geosynchronous earth orbit (GEO) satellite, and / or a highly elliptical orbit (HEO) satellite) can use one or more machine learning components (e.g., neural networks) that can be trained to learn a dependence of a quality of a measurement on individual parameters, isolate the quality of the measurement (also referred to as “operation”) through individual layers of the one or more machine learning components, and compress the measurement results in a manner that limits loss of compression. The client device can transmit the compressed measurement results to a server device (e.g., a TRP, another UE, and / or a base station). The server device can decode the compressed measurement results using one or more decompression operations and reconstruction operations associated with the one or more machine learning components. The one or more decompression and reconstruction operations can produce reconstructed measurement results based at least in part on a set of features of the compressed dataset. The server device can perform a wireless communication action based at least in part on the reconstructed measurement results.

[0060] A machine learning component is a component (e.g., hardware, software, or a combination thereof) of a client device that performs one or more machine learning processes. A machine learning component can include, for example, hardware and / or software that can learn to perform a process without being explicitly trained to perform the process. A machine learning component can include, for example, a feature learning processing block and / or a representation learning processing block. A machine learning component can include one or more neural networks. A neural network can include, for example, an autoencoder.

[0061] In some aspects, a machine learning component can be configured to determine a latent vector based at least in part on an observed wireless communication vector. In some aspects, the observed wireless communication vector and the latent vector can be associated with a wireless communication task. The observed wireless communication vector can include an array of observed values associated with one or more measurements obtained in connection with a wireless communication. In some aspects, for example, the wireless communication task can include determining channel state feedback (CSF), determining positioning information associated with a client device, determining a modulation associated with a wireless communication, and / or determining a waveform associated with a wireless communication. The latent vector h is an output of the machine learning component that takes as input the observed wireless communication vector. The latent vector can include an array of hidden values associated with one or more aspects of the observed communication vector.

[0062] In some cases, the machine learning component can be trained using federated learning. Federated learning is a machine learning technique that enables multiple clients to collaboratively learn a machine learning model based on training data without a server device collecting the training data from the client devices. Federated learning techniques can involve training one or more global neural network models from data stored on multiple client devices. For example, in a federated averaging algorithm, a server device sends a neural network model to the client devices. Each client device trains the received neural network model using its own data, and sends the updated neural network model back to the server device. The server device averages the updated neural network models from the client devices to obtain a new neural network model.

[0063] However, in some cases, some client devices can operate in different scenarios than other client devices (e.g., indoor / outdoor, stationary / moving in a coffee shop, etc.). In some cases, different client devices can belong to different implementation aspects (e.g., different form factors, different RF impairments, etc.). As a result, in some examples, it can be difficult to find a machine learning component model that works well on all devices in a federated learning network in terms of physical layer link performance.

[0064] To provide and train personalized machine learning components that are suitable for respective client devices, the machine learning component can be customized based on an environment of the client device. In some cases, an observed environment vector can be used to characterize an environment of the client device. The observed environment vector can include an array of observed values associated with one or more features of the environment of the client device. The environment of the client device can include any characteristic associated with the client device that can impact an operation of the client device, a signal received by the client device, and / or a signal transmitted by the client device. The operation of the client device can include any operation that can be performed on or in relation to any type of information. The operation of the client device can include, for example, receiving a signal, decoding a signal, demodulating a signal, processing a signal, encoding a signal, modulating a signal, and / or transmitting a signal. In some aspects, the one or more features of the environment of the client device can include a characteristic of the client device, a large scale channel characteristic, channel information, signal information, and / or image data, among other examples.

[0065] In some cases, for example, a number of machine learning components can be used by a client. One or more machine learning components can be configured to extract features about an environment of the client to determine a custom feature vector, a condition vector, and / or the like. The custom feature vector can be used to condition one or more additional machine learning components to work in the perceived environment. The custom feature vector and an observed wireless communication vector can be provided as input to the one or more additional machine learning components, which can be configured to perform a wireless communication task, such as by providing a latent vector, for example. The condition vector can include client-specific parameters that can be loaded into one or more other machine learning components to condition the one or more additional machine learning components to work in the perceived environment.

[0066] In some cases, a client device can provide an observed environment vector, a custom feature vector, a condition vector, and / or the like to a server device. The client device can also provide a latent vector to the server device, which can recover an observed wireless communication vector using one or more machine learning components corresponding to one or more machine learning components of the client device.

[0067] In some cases, a client device can receive machine learning components from a server device. The machine learning components can include, for example, neural network models, parameters corresponding to neural network models, sets of machine learning models, and / or the like. The client device can train the machine learning components based at least in part on training data obtained by the client device. For example, the client device can obtain training data based on observations of an environment of the client device and / or processing received signals.

[0068] However, the nature and / or scope of data collected by a client device can be influenced by any number of characteristics of the client device. For example, the complexity of the client device can influence the amount of data that can be collected by the client device (e.g., due to limited memory for storing data, limited processing capability for extracting and / or analyzing data, limited available power). In some cases, a client device can be configured to perform tasks having a higher priority than collecting data, updating machine learning components, and / or the like (e.g., communication, mobility management, beam management).

[0069] In some cases, a client device can collect a large amount of data, but that data can not be useful for training a machine learning component. In some cases, the collected data can be useful for training a machine learning component, but the performance of the machine learning component can not improve by training using that data. In some cases, the machine learning component can be improved, but can not be improved by a significant amount to warrant providing an update to the server device. For example, training data collected while the client device is stationary can not be useful for training the machine learning component with respect to a mobile environment. Thus, providing periodic updates of the machine learning component to the server device can be inefficient, and consume network processing and / or communication resources with little overall benefit, thereby negatively impacting network performance.

[0070] Aspects of the techniques and apparatuses described herein can facilitate machine learning component update reporting in federated learning. In some aspects, a client device can receive a reporting configuration that indicates a reporting condition. The reporting configuration can include an indication to report an update associated with a machine learning component based at least in part on the reporting condition. In this way, reporting of updates can be limited to cases in which the update can facilitate a useful update to a machine learning component maintained at a server device. As a result, aspects can lead to more efficient use of network resources in federated learning, thereby positively impacting network performance. Aspects of the techniques described herein can be used for any number of cross-node machine learning challenges including, for example, facilitating channel state feedback, facilitating positioning of client devices, and / or learning of modulations and / or waveforms for wireless communications.

[0071] Figure 3 FIG. 3 is a schematic diagram illustrating an example 300 of machine learning component update reporting in federated learning in accordance with the present disclosure. As shown, a number of client devices 302, 304, and 306 can be in communication with a server device 308. The client devices 302, 304, and 306 and the server device 308 can communicate with one another via a wireless network (e.g., the wireless network 100 shown in FIG. 1). In some cases, more than one client device 302, 304, 306 and / or more than one server device 308 can communicate with one another. Figure 1

[0072] ​Client devices 302, 304, and / or 306 and / or server device 308 may be, similar to, include, be incorporated in, or be implemented using a computing device. The computing device may include, for example, wireless communication devices, network devices (e.g., wireless network devices and / or wired network devices), portable computers, laptops, tablets, workstations, personal computers, controllers, vehicular control networks, IoT devices, traffic control devices, IAB nodes, UEs, base stations, relay stations, switches, routers, CPEs, vehicles (e.g., land-based vehicles, aircraft, non-ground vehicles, and / or water-based vehicles), and / or any combination thereof. For example, client device 302 may be a UE (e.g., Figure 1 The UE120 shown, and the server device 308 can be a base station (e.g., as shown in the figure). Figure 1 The base station 110 shown, as well as the client device 302 and server device 308, can communicate via an access link. The client device 302 and server device 308 can be UE 120 communicating via a side link.

[0073] Figure 3 Client device 302 is shown. Client devices 304 and / or 306 may be similar to client device 302 and / or may have the same or similar aspects as client device 302. As shown, client device 302 may include a first communication manager 310 (e.g., Figure 1 The first communication manager 140 shown can be configured to utilize a machine learning component (e.g., shown as a first client autoencoder) 312 to perform one or more wireless communication tasks. The first communication manager 310 can be configured to utilize... Figure 3 Any number of additional machine learning components not shown in the diagram.

[0074] As shown, the machine learning component 312 may include an encoder 314 configured to receive observed wireless communication vector x and provide a latent vector h as output. The machine learning component 312 may also include a decoder 316 configured to receive the latent vector h and provide the observed wireless communication vector x as output. Figure 3 As shown, server device 308 may include a second communication manager 318 (e.g., second communication manager 150) that can be configured to utilize a server machine learning component (e.g., shown as a server autoencoder) 320 to perform one or more wireless communication tasks. For example, in some aspects, server machine learning component 320 may correspond to client machine learning component 312. The second communication manager 318 can be configured to utilize... Figure 3Any additional machine learning components not shown. Server machine learning component 320 may include encoder 322, configured to receive observed wireless communication vector x as input and provide a latent vector h as output. Server machine learning component 320 may also include decoder 324, configured to receive latent vector h as input and provide observed wireless communication vector x as output.

[0075] like Figure 3 As shown, client device 302 may include a transceiver (shown as "Tx / Rx") 326 that can facilitate wireless communication with transceiver 328 of server device 308. As indicated by reference numeral 330, server device 308 may use transceiver 328 to transmit wireless communication to client device 302. The wireless communication may include, for example, a reference signal such as a Channel State Information Reference Signal (CSI-RS). Transceiver 326 of client device 302 may receive the wireless communication. Communication manager 310 may determine the observed wireless communication vector x based at least in part on the wireless communication. For example, in aspects where the wireless communication is CSI-RS, the observed wireless communication vector x may include Channel State Information (CSI).

[0076] As shown, the communication manager 310 can provide the observed wireless communication vector x as input to the encoder 314 of the client machine learning component 312. In some aspects, the communication manager 310 can also provide the encoder 314 as input to feature vectors associated with the environment of the client device 302. In some aspects, the communication manager 310 can also load client-specific parameters into one or more levels of the encoder 314. The encoder 314 of the client machine learning component 312 can determine a latent vector h based at least in part on the observed wireless communication vector x. As shown, the communication manager 310 can provide the latent vector h to the transceiver 326 for transmission. As indicated by reference numeral 332, the transceiver 326 can transmit the latent vector h, and the transceiver 328 of the server device 308 can receive the latent vector h. As shown, the communication manager 318 in the server device 308 can provide the latent vector h as input to the decoder 324 of the server machine learning component 320. The decoder 324 can determine (e.g., reconstruct) the observed wireless communication vector x based at least in part on the latent vector h. In some respects, server device 308 can perform wireless communication actions at least in part based on the observed wireless communication vector x. For example, in aspects of the observed wireless communication vector x including CSI, the communication manager 318 of server device 308 can use CSI for communication packetization, beamforming, etc.

[0077] Client devices 302, 304, and 306 can respectively use training data collected by client devices 302, 304, and 306 to train machine learning components locally. Client devices 302, 304, or 306 can optimize the model parameter set w associated with the machine learning component. (n) The system trains machine learning components (such as neural networks), where n is the joint learning round index. The set of client devices 302, 304, and 306 can be configured to provide updates to server device 308 multiple times (e.g., periodically, on demand, when updating local machine learning components, etc.). Each time server device 308 receives an update from client devices 302, 304, and 306 is called a round. The joint learning round index indicates the number of rounds since the last global update was sent by server device 308 to client devices 302, 304, and 306.

[0078] In some aspects, for example, the first communication manager 310 of the client device 302 can determine updates corresponding to the machine learning component 312 by training the machine learning component 312. In some aspects, the client device 302 can collect training data and store it in the memory device 334. The stored training data can be referred to as a "local dataset". In some aspects, the first communication manager 310 can access the training data from the memory device 334 and use the training data to generate training outputs from the machine learning component 312.

[0079] For example, as indicated by the dashed line associated with the first machine learning component 312, the decoder 316 can be used together with the training data to reconstruct wireless communication training vectors. The reconstructed training vectors can be used to facilitate the determination of model parameters w. (n) Model parameters w (n) Maximize the variational lower bound function. A negative variational lower bound function can correspond to the global loss function F(w) associated with the machine learning component. The stochastic gradient descent (SGD) algorithm can be used to optimize the model parameters w. (n) Client device 302 can execute one or more SGD processes to determine the optimization parameters w. (n) And the gradient of the loss function with respect to the loss function F(w) can be determined. Where k is the index that identifies the client device. The first communication manager 310 can also further refine the machine learning component 312, at least in part, based on the loss function value, gradient, etc.

[0080] By training the machine learning component, the first communication manager 310 can determine the update corresponding to the machine learning component 312. In some aspects, the update may include an updated set of model parameters w. (n) In the updated model parameter set w(n) the difference, gradient (n-1) between the previous model parameter set w updated machine learning component model, etc. The client device 302 can transmit the update or a compressed version thereof to the server device 308, as described below.

[0081] As shown by reference number 336, the server device 308 can transmit a reporting configuration, and the client device 302 can receive the reporting configuration. According to aspects, the reporting configuration can be carried in a downlink control information transmission, a radio resource control message, a medium access control (MAC) control element (CE), a random access channel (RACH) procedure, and / or the like. In some aspects, the reporting configuration can indicate whether the client device 302 is to update a machine learning component and / or provide an update to the server device 308.

[0082] In some aspects, the reporting configuration can indicate one or more reporting conditions, and can include an indication to report an update associated with a machine learning component based at least in part on the one or more reporting conditions. The one or more reporting conditions can correspond to an amount of training data collected by the client device 302. The one or more reporting conditions can include a data amount threshold. For example, in some aspects, the client device 302 can determine an amount of training data collected by the client device 302 during a collection period (e.g., a certain particular time period), and determine whether the amount of training data collected by the client device 302 (e.g., in samples, gigabytes, etc.) satisfies a data amount threshold.

[0083] As shown by reference number 338, the client device 302 can transmit the update to the server device 308 if the amount of collected training data satisfies the data amount threshold. According to aspects, the server device 308 can also receive updates for the machine learning component from the client device 304 and / or the client device 306. The second communications manager 318 can average the received updates, and update the server machine learning component 320 using the averaged update.

[0084] In some aspects, the client device 302 can transmit the update based at least in part on determining that the amount of training data collected by the client device satisfies the data amount threshold. In some aspects, the client device 302 can determine the update corresponding to the machine learning component based at least in part on determining that the amount of training data collected by the client device satisfies the data amount threshold.

[0085] In some aspects, the one or more reporting conditions can correspond to a performance of the machine learning component. In some aspects, for example, the one or more reporting conditions can correspond to a combination of a data volume threshold and a performance measure associated with the machine learning component. The “performance” of the machine learning component can refer to an accuracy with which the machine learning component performs a task for which it was designed. For example, a loss function value can be used to determine the performance of the machine learning component. For example, in some aspects, the one or more reporting conditions can include a loss function threshold. If the loss function value corresponding to the update satisfies the loss function threshold, the client device can transmit the update to the machine learning component.

[0086] In some aspects, the one or more reporting conditions can correspond to a loss function difference. The loss function difference can include a difference between a first loss function value associated with the machine learning component and a second loss function value associated with the machine learning component. The first loss function value can correspond to an initial instance of the machine learning component, and the second loss function value can correspond to an updated instance of the machine learning component. The initial instance of the machine learning component can be an instance at which the machine learning component was provided to the client device 302, a most recent (or otherwise previous) instance of the machine learning component, and the like.

[0087] In some aspects, for example, the client device 302 can receive initial machine learning component information. The initial machine learning component information can include an initial machine learning component, an initial set of parameters associated with the machine learning component, and the like. In some aspects, the client device 302 can determine a first loss function value, determine a second loss function value, and determine a loss function difference. The client device 302 can further determine whether the loss function difference satisfies a reporting condition. In some aspects, the client device 302 can transmit the update based at least in part on determining that the loss function difference satisfies the loss function threshold.

[0088] In some aspects, the one or more reporting conditions correspond to a use case associated with the machine learning component. The use case can include at least one of: CSI derivation, positioning measurement derivation, demodulation of a data channel, decoding of a data channel, or a combination thereof. The one or more reporting conditions can correspond to a data type associated with the set of collected data. The data type can include independent and identically distributed (I.I.D.) data. In some aspects, transmitting the update is based at least in part on determining that the set of collected data includes I.I.D. data. The one or more reporting conditions can indicate at least one communication resource to be used to report the update. The at least one communication resource includes at least one of a time resource or a frequency resource.

[0089] In some aspects, the client device 302 and / or the server device 308 can perform one or more additional operations. The client device 302 and / or the server device 308 can be configured to use, for example, one or more different types of machine learning components, to use one or more processes and / or components in addition to or instead of the one or more machine learning components. For example, in some aspects, the client device 302 and / or the server device 308 can be configured to perform a first type of process in relation to a received signal, and to perform a second type of process in relation to the received signal and / or another received signal. The first type of process can be performed using a first algorithm, a first processing block, and / or a first machine learning component, and the second type of process can be performed using a second algorithm, a second processing block, and / or a second machine learning component. In an example, the client device 302 can determine a first CSI associated with a received signal using a first process, and can determine a second CSI associated with the received signal and / or a different received signal using a second process.

[0090] As described above, Figure 3 are provided merely as examples. Other examples can differ from what is described Figure 3 with respect to the examples described with reference to

[0091] Figure 4 is a schematic diagram of an example 400 of machine learning component update reporting in federated learning, in accordance with the present disclosure. As shown, a client device 405 and a server device 410 can communicate with one another. In some aspects, the client device 405 can be, be similar to, include or be included in the client device 302 shown in FIG. 3. In some aspects, the server device 410 can be, be similar to, include or be included in the server device 308 shown in FIG. 3. Figure 3 Figure 3

[0092] As shown by reference number 415, the server device 410 can transmit a reporting configuration, which the client device 405 can receive. The reporting configuration can indicate one or more reporting conditions. The reporting configuration can include an indication to report, to the server device 410, an update associated with a machine learning component based at least in part on the one or more reporting conditions. In some aspects, the reporting configuration can indicate at least one communication resource to be used for reporting the update. For example, the reporting configuration can indicate a time resource, a frequency resource, and / or a spatial resource.

[0093] ​​The one or more reporting conditions can correspond to an amount of training data collected by the client device 405. For example, the one or more reporting conditions can include a data amount threshold. The one or more reporting conditions can correspond to a performance of the machine learning component. The one or more reporting conditions can correspond to a loss function value of the machine learning component. For example, the one or more reporting conditions can include a loss function value threshold. The one or more reporting conditions can correspond to a loss function difference, which can be a difference between a first loss function value associated with the machine learning component and a second loss function value associated with the machine learning component.

[0094] The one or more reporting conditions can correspond to a use case associated with the machine learning component. The use case can include at least one of: CSI derivation, positioning measurement derivation, demodulation of a data channel, decoding of a data channel, or a combination thereof. The one or more reporting conditions can correspond to a data type associated with the collected set of data. For example, the data type can include I.I.D. data. In some aspects, the one or more reporting conditions can include a combination of any of the reporting conditions explicitly indicated above and / or herein.

[0095] As shown by reference number 420, the client device 405 can collect training data. In some aspects, the reporting configuration can include an indication to determine an update for the machine learning component based at least in part on a determination that an amount of the collected training data satisfies a data amount threshold. As shown by reference number 425, the client device 405 can determine the update. The client device 405 can determine the update based at least in part on a determination that the amount of the collected training data satisfies the data amount threshold, for example.

[0096] As shown by reference number 430, the client device 405 can determine that the one or more reporting conditions are satisfied. As shown by reference number 435, the client device 405 can transmit the machine learning component update, and the server device 410 can receive the machine learning component update. In some aspects, the client device 405 can transmit the machine learning component update based at least in part on a determination that the one or more reporting conditions are satisfied.

[0097] As shown by reference number 440, the client device 405 can determine that an additional update associated with the machine learning component fails to satisfy the one or more reporting conditions. The client device 405 can refrain from transmitting the additional update to the server device 410 based at least in part on a determination that the additional update fails to satisfy the one or more reporting conditions.

[0098] In some aspects, as shown by reference number 445, the client device 405 can transmit, to the server device 410, an indication that the client device is refraining from transmitting additional updates (shown as “no update report”). In some aspects, the client device 405 can transmit, in the report, an indication that the client is refraining from transmitting additional updates. For example, in some aspects, two different report types can be utilized: a first type for transmitting updates to the machine learning component, and a second type for transmitting an indication that the client device 405 is refraining from transmitting updates. In some aspects, the client device 405 can transmit, in the report, at least one of a loss function value associated with a training dataset or a loss function value associated with a validation dataset.

[0099] In some aspects, the server device 410 can configure (e.g., using a report configuration) time, frequency, and / or spatial resources for transmitting the two types of reports. Based on the resources used by the client device 405 to transmit the report, the server device 410 can identify the type of report. In some aspects, the server device 410 can perform a blind detection procedure to identify whether the client device 405 has transmitted a report.

[0100] In some aspects, the second type of report can indicate a reporting delay. The reporting delay can include at least one time resource or frequency resource during which the client device 405 will refrain from reporting updates. In some aspects, the second type of report can indicate a current instance of the machine learning component. In this way, the server device 410 can know that the current instance of the machine learning component is relevant to processing the signal.

[0101] As described above, Figure 4 are provided merely by way of example. Other examples can differ from Figure 4 the examples described with respect to the examples described with respect to

[0102] the examples described with respect to Figure 5 is a schematic illustration of an example process 500 performed, for example, by a client device, in accordance with the present disclosure. Example process 500 is an example of a process for a client device (e.g., client device 302 shown in Figure 3 , client device 405 shown in Figure 4 to perform operations associated with machine learning component update reporting in federated learning.

[0103] As described above, Figure 5 in some aspects, process 500 can include receiving a report configuration indicating one or more reporting conditions, where the report configuration further indicates that, based at least in part on the one or more reporting conditions being satisfied, the client device is to report updates associated with a machine learning component (block 510). For example, the client device can receive (e.g., using a report configuration component 415 shown in Figure 7The reception component 702, depicted in FIG. 7A, receives a report configuration indicating one or more reporting conditions, where the report configuration further indicates that, based at least in part on the one or more reporting conditions being satisfied, the client device is to report an update associated with the machine-learned component, as described above.

[0104] As further shown in Figure 5 In some aspects, process 500 can include transmitting, to the server device, the update associated with the machine-learned component based at least in part on whether the one or more reporting conditions are satisfied (block 520), as further described below. Figure 7 The transmission component 706, depicted in FIG. 7A, can transmit, to the server device, the update associated with the machine-learned component based at least in part on whether the one or more reporting conditions are satisfied. For example, process 500 can include transmitting the update based at least in part on determining that the one or more reporting conditions are satisfied, or refraining from transmitting the update associated with the machine-learned component to the server device based at least in part on determining that the one or more reporting conditions are not satisfied.

[0105] Process 500 can include additional aspects, such as any single aspect or any combination of aspects described below and / or in connection with one or more other processes described elsewhere herein.

[0106] In a first aspect, the machine-learned component includes at least one neural network.

[0107] In a second aspect, alone or in combination with the first aspect, the one or more reporting conditions correspond to an amount of training data collected by the client device.

[0108] In a third aspect, alone or in combination with one or more of the first and second aspects, the one or more reporting conditions include a data amount threshold, the method further comprising determining an amount of training data collected by the client device during a collection period, and determining that the amount of training data collected by the client device satisfies the data amount threshold, wherein transmitting the update comprises transmitting the update based at least in part on determining that the amount of training data collected by the client device satisfies the data amount threshold.

[0109] In a fourth aspect, alone or in combination with one or more of the first through third aspects, process 500 includes training the machine-learned component based at least in part on determining that the amount of training data collected by the client device satisfies the data amount threshold.

[0110] In a fifth aspect, alone or in combination with one or more of the first through fourth aspects, the one or more reporting conditions correspond to a performance of the machine-learned component.

[0111] In a sixth aspect, alone or in combination with one or more of the first through fifth aspects, the one or more reporting conditions correspond to a loss function value of the machine learning component.

[0112] In a seventh aspect, alone or in combination with one or more of the first through sixth aspects, the one or more reporting conditions correspond to a loss function difference, wherein the loss function difference comprises a difference between a first loss function value associated with the machine learning component and a second loss function value associated with the machine learning component.

[0113] In an eighth aspect, alone or in combination with one or more of the first through seventh aspects, the first loss function value corresponds to an initial instance of the machine learning component, and the second loss function value corresponds to an updated instance of the machine learning component.

[0114] In a ninth aspect, alone or in combination with one or more of the first through eighth aspects, the process 500 includes receiving initial machine learning component information, and determining the initial instance of the machine learning component based at least in part on the initial machine learning component information.

[0115] In a tenth aspect, alone or in combination with one or more of the first through ninth aspects, the process 500 includes determining the first loss function value, determining the second loss function value, determining the loss function difference, and determining that the loss function difference satisfies a reporting condition, wherein transmitting the update comprises transmitting the update based at least in part on determining that the loss function difference satisfies a loss function difference threshold.

[0116] In an eleventh aspect, alone or in combination with one or more of the first through tenth aspects, the one or more reporting conditions correspond to a use case associated with the machine learning component.

[0117] In a twelfth aspect, alone or in combination with one or more of the first through eleventh aspects, the use case comprises at least one of: channel state information derivation, positioning measurement derivation, demodulation of a data channel, decoding of a data channel, or a combination thereof.

[0118] In a thirteenth aspect, alone or in combination with one or more of the first through twelfth aspects, the one or more reporting conditions correspond to a data type associated with the set of collected data.

[0119] In a fourteenth aspect, alone or in combination with one or more of the first through thirteenth aspects, the data type comprises identically independently distributed data, wherein transmitting the update is based at least in part on determining that the set of collected data comprises the identically independently distributed data.

[0120] In a fifteenth aspect, alone or in combination with one or more of the first through fourteenth aspects, the report configuration indicates at least one communication resource to be used for reporting the update.

[0121] In a sixteenth aspect, alone or in combination with one or more of the first through fifteenth aspects, the at least one communication resource comprises at least one of a time resource or a frequency resource.

[0122] In a seventeenth aspect, alone or in combination with one or more of the first through sixteenth aspects, the process 500 includes sending, to the server device, an indication that the client device is refraining from sending updates.

[0123] In an eighteenth aspect, alone or in combination with one or more of the first through seventeenth aspects, sending the update to the server device comprises sending a first type of report, and sending the indication to the server device that the client device is refraining from sending updates comprises sending a second type of report.

[0124] In a nineteenth aspect, alone or in combination with one or more of the first through eighteenth aspects, the second type of report indicates a reporting delay.

[0125] In a twentieth aspect, alone or in combination with one or more of the first through nineteenth aspects, the reporting delay comprises at least one time resource or frequency resource during which the client device will refrain from reporting additional updates.

[0126] In a twenty-first aspect, alone or in combination with one or more of the first through twentieth aspects, the second type of report indicates a current instance of a machine learning component.

[0127] In a twenty-second aspect, alone or in combination with one or more of the first through twenty-first aspects, the second type of report indicates at least one of a loss function value associated with a training data set or a loss function value associated with a validation data set.

[0128] In a twenty-third aspect, alone or in combination with one or more of the first through twenty-second aspects, the client device comprises a user equipment, and the server device comprises a base station.

[0129] Although Figure 5 Example blocks of the process 500 are shown, but in some aspects, the process 500 can include additional blocks, fewer blocks, different blocks, or differently arranged blocks than those depicted in FIG. 5. Additionally, or alternatively, two or more of the blocks of the process 500 can be performed in parallel. Figure 5 Example blocks of the process 500 are shown, but in some aspects, the process 500 can include additional blocks, fewer blocks, different blocks, or differently arranged blocks than those depicted in FIG. 5. Additionally, or alternatively, two or more of the blocks of the process 500 can be performed in parallel.

[0130] Figure 6 is a schematic diagram illustrating an example process 600, for example, performed by a server device, in accordance with the present disclosure. The example process 600 is an example of a process performed by a server device (e.g., the server device 308 shown in Figure 3 the server device 410 shown in FIG. 4) to perform operations associated with machine learning component update reporting in federated learning. Figure 4

[0131] As shown in Figure 6 In some aspects, the process 600 can include transmitting, to the client device, a reporting configuration indicating one or more reporting conditions, where the reporting configuration further indicates that the client device is to report an update associated with the machine learning component based at least in part on the one or more reporting conditions being satisfied (block 610). For example, the server device can transmit, to the client device (e.g., using the transmission component 906 depicted in FIG. 9), a reporting configuration indicating one or more reporting conditions, where the reporting configuration further indicates that the client device is to report an update associated with the machine learning component based at least in part on the one or more reporting conditions being satisfied, as described above. Figure 9

[0132] As further shown in Figure 6 In some aspects, the process 600 can include receiving, from the client device, an update associated with the machine learning component based at least in part on whether the one or more reporting conditions are satisfied (block 620). For example, the server device (e.g., using the reception component 902 depicted in FIG. 9) can receive, from the client device, an update associated with the machine learning component based at least in part on whether the one or more reporting conditions are satisfied. For instance, the server device can receive the update based at least in part on determining that the one or more reporting conditions are satisfied, or fail to receive an update associated with the machine learning component from the client device based at least in part on determining that the one or more reporting conditions are not satisfied. Figure 9

[0133] Process 600 can include additional aspects, such as any single aspect or any combination of aspects described below and / or in connection with one or more other processes described elsewhere herein.

[0134] In a first aspect, the machine learning component comprises at least one neural network.

[0135] In a second aspect, alone or in combination with the first aspect, the one or more reporting conditions correspond to an amount of training data collected by the client device.

[0136] ​​​In a third aspect, alone or in combination with one or more of the first and second aspects, the one or more reporting conditions include a data volume threshold, wherein receiving the update includes receiving the update based at least in part on determining that an amount of training data collected by the client device satisfies the data volume threshold.

[0137] In a fourth aspect, alone or in combination with one or more of the first through third aspects, the reporting configuration includes an indication to train the machine learning component based at least in part on determining that an amount of training data collected by the client device satisfies a data volume threshold.

[0138] In a fifth aspect, alone or in combination with one or more of the first through fourth aspects, the one or more reporting conditions correspond to a performance of the machine learning component.

[0139] In a sixth aspect, alone or in combination with one or more of the first through fifth aspects, the one or more reporting conditions correspond to a loss function value of the machine learning component.

[0140] In a seventh aspect, alone or in combination with one or more of the first through sixth aspects, the one or more reporting conditions correspond to a loss function difference, wherein the loss function difference includes a difference between a first loss function value associated with the machine learning component and a second loss function value associated with the machine learning component.

[0141] In an eighth aspect, alone or in combination with one or more of the first through seventh aspects, the first loss function value corresponds to an initial instance of the machine learning component and the second loss function value corresponds to an updated instance of the machine learning component.

[0142] In a ninth aspect, alone or in combination with one or more of the first through eighth aspects, receiving the update includes receiving the update based at least in part on the loss function difference satisfying a loss function difference threshold.

[0143] In a tenth aspect, alone or in combination with one or more of the first through ninth aspects, the one or more reporting conditions correspond to a use case associated with the machine learning component.

[0144] In an eleventh aspect, alone or in combination with one or more of the first through tenth aspects, the use case includes at least one of: channel state information derivation, positioning measurement derivation, demodulation of a data channel, decoding of a data channel, or a combination thereof.

[0145] In a twelfth aspect, alone or in combination with one or more of the first through eleventh aspects, the one or more reporting conditions correspond to a data type associated with the set of collected data.

[0146] In a thirteenth aspect, alone or in combination with one or more of the first through twelfth aspects, the data type comprises identically distributed data, wherein receiving the update is based at least in part on determining that the collected set of data comprises identically distributed data.

[0147] In a fourteenth aspect, alone or in combination with one or more of the first through thirteenth aspects, the report configuration indicates at least one communication resource to be used for reporting the update.

[0148] In a fifteenth aspect, alone or in combination with one or more of the first through fourteenth aspects, the at least one communication resource comprises at least one of a time resource or a frequency resource.

[0149] In a sixteenth aspect, alone or in combination with one or more of the first through fifteenth aspects, the process 600 comprises determining that the update is not received from the client device.

[0150] In a seventeenth aspect, alone or in combination with one or more of the first through sixteenth aspects, determining that the update is not received from the client device comprises performing a blind detection process.

[0151] In an eighteenth aspect, alone or in combination with one or more of the first through seventeenth aspects, determining that the update is not received from the client device comprises receiving an indication from the client device that the client device is refraining from sending the update.

[0152] In a nineteenth aspect, alone or in combination with one or more of the first through eighteenth aspects, receiving the update from the client device comprises receiving a first type of report, and receiving the indication from the client device that the client device is refraining from sending the update comprises receiving a second type of report.

[0153] In a twentieth aspect, alone or in combination with one or more of the first through nineteenth aspects, the second type of report indicates a reporting delay.

[0154] In a twenty-first aspect, alone or in combination with one or more of the first through twentieth aspects, the reporting delay comprises at least one time resource or frequency resource during which the client device will refrain from reporting additional updates.

[0155] In a twenty-second aspect, alone or in combination with one or more of the first through twenty-first aspects, the second type of report indicates a current instance of a machine learning component.

[0156] In a twenty-third aspect, alone or in combination with one or more of the first through twenty-second aspects, the second type of report indicates at least one of a loss function value associated with the training data set or a loss function value associated with the validation data set.

[0157] In a twenty-fourth aspect, alone or in combination with one or more of the first through twenty-third aspects, the client device comprises a user equipment, and the server device comprises a base station.

[0158] Although Figure 6 example blocks of process 600, in some aspects, process 600 can include additional blocks, fewer blocks, different blocks, or differently arranged blocks than those depicted in Figure 6 Additionally or alternatively, two or more of the blocks of process 600 can be performed in parallel.

[0159] Figure 7 is a block diagram of an example apparatus 700 for wireless communication in accordance with the present disclosure. The apparatus 700 can be, be similar to, include, or be included in a client device (e.g., a client device 302 as illustrated in Figure 3 and / or a client device 405 as illustrated in Figure 4 In some aspects, the apparatus 700 includes a reception component 702, a communication manager 704, and a transmission component 706, which can be in communication with one another (for example, via one or more buses). As shown, the apparatus 700 can communicate with another apparatus 708 (such as a client device, a server, a UE, a base station, or another wireless communication device) using the reception component 702 and the transmission component 706.

[0160] In some aspects, the apparatus 700 can be configured to perform one or more operations described herein with regard to the method 400. Additionally or alternatively, the apparatus 700 can be configured to perform one or more processes described herein, such as process 500. Figure 3 and / or Figure 4 In some aspects, the apparatus 700 can include one or more components of the first UE described above in connection with Fig. 2. Figure 5 Figure 2

[0161] ​​The reception component 702 can provide means for receiving communications (such as reference signals, control information, data communications, or combinations thereof) from the apparatus 708. The reception component 702 can provide received communications to one or more other components of the apparatus 700, such as the communication manager 704. In some aspects, the reception component 702 can provide means for performing signal processing on the received communications (such as filtering, amplification, demodulation, analog-to-digital conversion, demultiplexing, deinterleaving, de-mapping, equalization, interference cancellation, or decoding, among other examples), and can provide the processed signals to the one or more other components. In some aspects, the reception component 702 can include one or more antennas, a demodulator, a MIMO detector, a receive processor, a controller / processor, a memory, or combinations thereof, of the first UE described above. Figure 2 The reception component 702 can provide means for receiving communications (such as reference signals, control information, data communications, or combinations thereof) from the apparatus 708. The reception component 702 can provide received communications to one or more other components of the apparatus 700, such as the communication manager 704. In some aspects, the reception component 702 can provide means for performing signal processing on the received communications (such as filtering, amplification, demodulation, analog-to-digital conversion, demultiplexing, deinterleaving, de-mapping, equalization, interference cancellation, or decoding, among other examples), and can provide the processed signals to the one or more other components. In some aspects, the reception component 702 can include one or more antennas, a demodulator, a MIMO detector, a receive processor, a controller / processor, a memory, or combinations thereof, of the first UE described above.

[0162] The transmission component 706 can provide means for transmitting communications (such as reference signals, control information, data communications, or combinations thereof) to the apparatus 708. In some aspects, the communication manager 704 can generate communications and can transmit the generated communications to the transmission component 706 for transmission to the apparatus 708. In some aspects, the transmission component 706 can provide means for performing signal processing on generated communications (such as filtering, amplification, modulation, digital-to-analog conversion, multiplexing, interleaving, mapping, or encoding, among other examples), and can transmit the processed signals to the apparatus 708. In some aspects, the transmission component 706 can include one or more antennas, a modulator, a transmit MIMO processor, a transmit processor, a controller / processor, a memory, or combinations thereof, of the first UE described above. In some aspects, the transmission component 706 can be collocated with the reception component 702 in a transceiver. Figure 2 The transmission component 706 can provide means for transmitting communications (such as reference signals, control information, data communications, or combinations thereof) to the apparatus 708. In some aspects, the communication manager 704 can generate communications and can transmit the generated communications to the transmission component 706 for transmission to the apparatus 708. In some aspects, the transmission component 706 can provide means for performing signal processing on generated communications (such as filtering, amplification, modulation, digital-to-analog conversion, multiplexing, interleaving, mapping, or encoding, among other examples), and can transmit the processed signals to the apparatus 708. In some aspects, the transmission component 706 can include one or more antennas, a modulator, a transmit MIMO processor, a transmit processor, a controller / processor, a memory, or combinations thereof, of the first UE described above. In some aspects, the transmission component 706 can be collocated with the reception component 702 in a transceiver.

[0163] In some aspects, the communication manager 704 can provide means for receiving a reporting configuration that indicates one or more reporting conditions, where the reporting configuration further indicates that, based at least in part on the one or more reporting conditions being satisfied, the client device is to report an update associated with the machine learning component and, based at least in part on whether the one or more reporting conditions are satisfied, transmit the update associated with the machine learning component to the server device. In some aspects, the communication manager 704 can include a reception component 702, a transmission component 706, and / or the like. In some aspects, the means provided by the communication manager 704 can include or be included in the means provided by the reception component 702, the transmission component 706, and / or the like. Figure 2 In some aspects, the communication manager 704 can provide means for receiving a reporting configuration that indicates one or more reporting conditions, where the reporting configuration further indicates that, based at least in part on the one or more reporting conditions being satisfied, the client device is to report an update associated with the machine learning component and, based at least in part on whether the one or more reporting conditions are satisfied, transmit the update associated with the machine learning component to the server device. In some aspects, the communication manager 704 can include a reception component 702, a transmission component 706, and / or the like. In some aspects, the means provided by the communication manager 704 can include or be included in the means provided by the reception component 702, the transmission component 706, and / or the like.

[0164] In some aspects, the communication manager 704 and / or one or more components of the communication manager 704 can include hardware (e.g., one or more circuits of the circuitry described in connection with Fig. 20) or can be implemented by such hardware. In some aspects, the communication manager 704 and / or one or more components of the communication manager 704 can include, be, or can be implemented by, the controller / processor, the memory, the scheduler, the communication unit, or a combination thereof, of the UE 120 described above in connection with Fig. 2. Figure 2 In some aspects, the communication manager 704 and / or one or more components of the communication manager 704 can include hardware (e.g., one or more circuits of the circuitry described in connection with Fig. 20) or can be implemented by such hardware. In some aspects, the communication manager 704 and / or one or more components of the communication manager 704 can include, be, or can be implemented by, the controller / processor, the memory, the scheduler, the communication unit, or a combination thereof, of the UE 120 described above in connection with Fig. 2. Figure 2 In some aspects, the communication manager 704 and / or one or more components of the communication manager 704 can include hardware (e.g., one or more circuits of the circuitry described in connection with Fig. 20) or can be implemented by such hardware. In some aspects, the communication manager 704 and / or one or more components of the communication manager 704 can include, be, or can be implemented by, the controller / processor, the memory, the scheduler, the communication unit, or a combination thereof, of the UE 120 described above in connection with Fig. 2.

[0165] In some aspects, the communication manager 704 and / or one or more components of the communication manager 704 can be implemented in code (e.g., as software or firmware stored in the memory), which can be executed by a controller or processor. If implemented in code, the functions of the communication manager 704 and / or a component thereof can be executed by a controller or processor, which can be a processor 202, a memory 204, a scheduler 206, a communication unit 208, or a combination thereof, of the UE 120 described above in connection with Fig. 2. Figure 2 In some aspects, the communication manager 704 and / or one or more components of the communication manager 704 can include hardware (e.g., one or more circuits of the circuitry described in connection with Fig. 20) or can be implemented by such hardware. In some aspects, the communication manager 704 and / or one or more components of the communication manager 704 can include, be, or can be implemented by, the controller / processor, the memory, the scheduler, the communication unit, or a combination thereof, of the UE 120 described above in connection with Fig. 2.

[0166] Figure 7 The number and arrangement of components shown in FIG. 8 are provided as an example. In practice, there can be additional components, fewer components, different components, or differently arranged components than those shown in FIG. 8. Additionally, or alternatively, two or more components shown in FIG. 8 can be implemented within a single component, and / or a single component shown in FIG. 8 can be implemented as multiple, distributed components. Additionally, or alternatively, a set of components (e.g., one or more components) shown in FIG. 8 can perform one or more functions described as being performed by another set of components shown in FIG. 8. Figure 7 The number and arrangement of components shown in FIG. 8 are provided as an example. In practice, there can be additional components, fewer components, different components, or differently arranged components than those shown in FIG. 8. Additionally, or alternatively, two or more components shown in FIG. 8 can be implemented within a single component, and / or a single component shown in FIG. 8 can be implemented as multiple, distributed components. Additionally, or alternatively, a set of components (e.g., one or more components) shown in FIG. 8 can perform one or more functions described as being performed by another set of components shown in FIG. 8. Figure 7 The number and arrangement of components shown in FIG. 8 are provided as an example. In practice, there can be additional components, fewer components, different components, or differently arranged components than those shown in FIG. 8. Additionally, or alternatively, two or more components shown in FIG. 8 can be implemented within a single component, and / or a single component shown in FIG. 8 can be implemented as multiple, distributed components. Additionally, or alternatively, a set of components (e.g., one or more components) shown in FIG. 8 can perform one or more functions described as being performed by another set of components shown in FIG. 8. Figure 7 The number and arrangement of components shown in FIG. 8 are provided as an example. In practice, there can be additional components, fewer components, different components, or differently arranged components than those shown in FIG. 8. Additionally, or alternatively, two or more components shown in FIG. 8 can be implemented within a single component, and / or a single component shown in FIG. 8 can be implemented as multiple, distributed components. Additionally, or alternatively, a set of components (e.g., one or more components) shown in FIG. 8 can perform one or more functions described as being performed by another set of components shown in FIG. 8. Figure 7 The number and arrangement of components shown in FIG. 8 are provided as an example. In practice, there can be additional components, fewer components, different components, or differently arranged components than those shown in FIG. 8. Additionally, or alternatively, two or more components shown in FIG. 8 can be implemented within a single component, and / or a single component shown in FIG. 8 can be implemented as multiple, distributed components. Additionally, or alternatively, a set of components (e.g., one or more components) shown in FIG. 8 can perform one or more functions described as being performed by another set of components shown in FIG. 8. Figure 7 The number and arrangement of components shown in FIG. 8 are provided as an example. In practice, there can be additional components, fewer components, different components, or differently arranged components than those shown in FIG. 8. Additionally, or alternatively, two or more components shown in FIG. 8 can be implemented within a single component, and / or a single component shown in FIG. 8 can be implemented as multiple, distributed components. Additionally, or alternatively, a set of components (e.g., one or more components) shown in FIG. 8 can perform one or more functions described as being performed by another set of components shown in FIG. 8. The number and arrangement of components shown in FIG. 8 are provided as an example. In practice, there can be additional components, fewer components, different components, or differently arranged components than those shown in FIG. 8. Additionally, or alternatively, two or more components shown in FIG. 8 can be implemented within a single component, and / or a single component shown in FIG. 8 can be implemented as multiple, distributed components. Additionally, or alternatively, a set of components (e.g., one or more components) shown in FIG. 8 can perform one or more functions described as being performed by another set of components shown in FIG. 8.

[0167] The number and arrangement of components shown in FIG. 8 are provided as an example. In practice, there can be additional components, fewer components, different components, or differently arranged components than those shown in FIG. 8. Additionally, or alternatively, two or more components shown in FIG. 8 can be implemented within a single component, and / or a single component shown in FIG. 8 can be implemented as multiple, distributed components. Additionally, or alternatively, a set of components (e.g., one or more components) shown in FIG. 8 can perform one or more functions described as being performed by another set of components shown in FIG. 8. Figure 8 is a schematic diagram illustrating an example 800 of a hardware implementation for an apparatus 802 employing a processing system 804. The apparatus 802 can be, be similar to, include, or be included in the apparatus 700 shown in FIG. 7. Figure 7 is a schematic diagram illustrating an example 800 of a hardware implementation for an apparatus 802 employing a processing system 804. The apparatus 802 can be, be similar to, include, or be included in the apparatus 700 shown in FIG. 7.

[0168] The processing system 804 can be implemented within a bus architecture, generally represented by the bus 806. The bus 806 can include any number of interconnecting buses and bridges depending on the specific application of the processing system 804 and the overall design constraints. The bus 806 links together various circuits including one or more processors and / or hardware components, represented by the processor 808, the components shown in the figure, and the computer-readable medium / memory 810. The bus 806 can also link various other circuits such as timing sources, peripherals, voltage regulators, power management circuits, and the like.

[0169] The processing system 804 can be coupled to a transceiver 812. The transceiver 812 is coupled to one or more antennas 814. The transceiver 812 provides a means for communicating with various other apparatus over a transmission medium. The transceiver 812 receives a signal from the one or more antennas 814, extracts information from the received signal, and provides the extracted information to the processing system 804, specifically the reception component 816. In addition, the transceiver 812 receives information from the processing system 804, specifically the transmission component 818, and

[0170] The processor 808 is coupled to the computer-readable medium / memory 810. The processor 808 is responsible for general processing, including the execution of software stored on the computer-readable medium / memory 810. The software, when executed by the processor 808, causes the processing system 804 to perform the various functions described herein in connection with a client. The computer-readable medium / memory 810 can also reside in the processing system 804. The computer-readable medium / memory 810 can further be used for storing data that is manipulated by the processor 808 when executing software. The processing system 804 can further include a communications manager 820 and / or Figure 8 The components shown in the figure, and / or any number of additional components, not shown, can be used to implement the functions described herein. The components shown and / or not shown can be software modules running in the processor 808, resident / stored in the computer-readable medium / memory 810, one or more hardware modules coupled to the processor 808, or some combination thereof.

[0171] In some aspects, the processing system 804 can be a component of the UE 120 and can include the memory 282 and / or at least one of the TX MIMO processor 266, the RX processor 258, and / or the controller / processor 280. In some aspects, the apparatus 802 for wireless communication provides means for receiving a reporting configuration that indicates one or more reporting conditions, where the reporting configuration further indicates that, based at least in part on the one or more reporting conditions being satisfied, the client device is to report an update associated with a machine learning component to the server device and, based at least in part on whether the one or more reporting conditions are satisfied, transmit the update associated with the machine learning component to the server device. The aforementioned means can be one or more of the aforementioned components of the processing system 804 configured to perform the functions recited by the aforementioned means. As described elsewhere herein, the processing system 804 can include the TX MIMO processor 266, the RX processor 258, and / or the controller / processor 280. In one configuration, the aforementioned means can be the TX MIMO processor 266, the RX processor 258, and / or the controller / processor 280 configured to perform the functions and / or operations recited herein.

[0172] Figure 8 are provided as examples. Other examples can differ from what is described Figure 8 with respect to the examples described with reference to

[0173] Figure 9 is a block diagram of an example apparatus 900 for wireless communication in accordance with the present disclosure. The apparatus 900 can be, be similar to, include, or be included in a server device (e.g., the server device 308 shown in Figure 3 and / or the server device 410 shown in Figure 4 In some aspects, the apparatus 900 includes a reception component 902, a communication manager 904, and a transmission component 906, which can be in communication with one another (for example, via one or more buses). As shown, the apparatus 900 can communicate with another apparatus 908 (such as a client, a server, a UE, a base station, or another wireless communication device) using the reception component 902 and the transmission component 906.

[0174] In some aspects, the apparatus 900 can be configured to perform one or more operations described herein with reference to Figure 3 and / or Figure 4 In addition, or in the alternative, the apparatus 900 can be configured to perform one or more processes described herein, such as the process 600 of Figure 6 In some aspects, the apparatus 900 can include one or more components of the base station described above in connection with Figure 2

[0175] ​Receiver component 902 may provide units for receiving communications (such as reference signals, control information, data communications, or combinations thereof) from device 908. Receiver component 902 may provide the received communications to one or more other components of device 900 (such as communication manager 904). In some aspects, receiver component 902 may provide units for performing signal processing on the received communications (such as filtering, amplification, demodulation, analog-to-digital conversion, demultiplexing, deinterleaving, demapping, equalization, interference cancellation, or decoding, and other examples), and for providing the processed signals to one or more other components. In some aspects, receiver component 902 may include elements combined with the above. Figure 2 The described base station includes one or more antennas, demodulators, MIMO detectors, receiver processors, controllers / processors, memory, or combinations thereof.

[0176] Transmitting component 906 may provide units for transmitting communications (such as reference signals, control information, data communications, or combinations thereof) to device 908. In some aspects, communication manager 904 may generate communications and transmit the generated communications to transmitting component 906 for transmission to device 908. In some aspects, transmitting component 906 may provide units for performing signal processing (e.g., filtering, amplification, modulation, digital-to-analog conversion, multiplexing, interleaving, mapping, or encoding, and other examples) on the generated communications and transmitting the processed signals to device 908. In some aspects, transmitting component 906 may include elements combined with the above. Figure 2 The described base station includes one or more antennas, modulators, transmit MIMO processors, transmit processors, controllers / processors, memory, or combinations thereof. In some aspects, the transmit component 906 may be co-located with the receive component 902 in a transceiver.

[0177] The communication manager 904 may provide units for sending a report configuration indicating one or more reporting conditions to a client device, wherein the report configuration further indicates that the client device will report an update associated with the machine learning component based at least in part on the satisfaction of one or more reporting conditions; and units for receiving the update associated with the machine learning component from the client device based at least in part on the determination that one or more reporting conditions are satisfied, or for failing to receive the update associated with the machine learning component destined for the server device based at least in part on the determination that one or more reporting conditions are not satisfied. In some aspects, the communication manager 904 may include the above-described combination of... Figure 2 The described base station includes a controller / processor, memory, scheduler, communication unit, or a combination thereof. In some aspects, the communication manager 904 may include a receiving component 902, a transmitting component 906, etc. In some aspects, the units provided by the communication manager 904 may include or be included within the units provided by the receiving component 902, the transmitting component 906, etc.

[0178] In some aspects, the communication manager 904 and / or one or more components thereof can include hardware (e.g., one or more circuits of the circuitry described in connection with Fig. 13) or can be implemented within such hardware. In some aspects, the communication manager 904 and / or one or more components thereof can include, be, or can be implemented by, the controller / processor, memory, or combination thereof of the BS 90 described above in connection with Figure 2 In some aspects, the communication manager 904 and / or one or more components thereof can include, be, or can be implemented by, the controller / processor, memory, or combination thereof of the BS 90 described above in connection with Figure 2 In some aspects, the communication manager 904 and / or one or more components thereof can include, be, or can be implemented by, the controller / processor, memory, or combination thereof of the BS 90 described above in connection with

[0179] In some aspects, the communication manager 904 and / or one or more components thereof can be implemented in code (e.g., as software or firmware stored in memory), which can be executed by a controller or processor. If implemented in code, the functions of the communication manager 904 and / or a component thereof can be executed by a controller or processor, using Figure 2 In some aspects, the communication manager 904 and / or one or more components thereof can be implemented in code (e.g., as software or firmware stored in memory), which can be executed by a controller or processor. If implemented in code, the functions of the communication manager 904 and / or a component thereof can be executed by a controller or processor, using

[0180] Figure 9 The number and arrangement of components shown in FIG. 10 are provided as an example. In practice, there can be additional components, fewer components, different components, or differently arranged components than those shown in FIG. 10. Additionally, or alternatively, Figure 9 Two or more components shown in FIG. 10 can be implemented within a single component, or Figure 9 A single component shown in FIG. 10 can be implemented as multiple, distributed components. Additionally or alternatively, Figure 9 A set of one or more components shown in FIG. 10 can perform one or more functions described as being performed by another set of one or more components shown in FIG. 10. Figure 9 A set of one or more components shown in FIG. 10 can perform one or more functions described as being performed by another set of one or more components shown in FIG. 10. Figure 10 A set of one or more components shown in FIG. 10 can perform one or more functions described as being performed by another set of one or more components shown in FIG. 10.

[0181] Figure 9 is a schematic diagram illustrating an example 1000 of a hardware implementation for an apparatus 1002 employing a processing system 1004. The apparatus 1002 can be, similar to, include, or be included in the apparatus 900 shown in FIG. 10. Figure 10

[0182] ​The processing system 1004 can be implemented within a bus architecture, generally represented by the bus 1006. The bus 1006 can include any number of interconnecting buses and bridges depending on the specific application of the processing system 1004 and the overall design constraints. The bus 1006 links together various circuits including one or more processors and / or hardware components represented by the processor 1008, the components shown in the figure, and the computer-readable medium / memory 1010. The bus 1006 can also link various other circuits such as timing sources, peripherals, voltage regulators, power management circuits, and the like.

[0183] The processing system 1004 can be coupled to a transceiver 1012. The transceiver 1012 is coupled to one or more antennas 1014. The transceiver 1012 provides a means for communicating with various other apparatus over a transmission medium. The transceiver 1012 receives a signal from the one or more antennas 1014, extracts information from the received signal, and provides the extracted information to the processing system 1004, specifically the reception component 1016. In addition, the transceiver 1012 receives information from the processing system 1004, specifically the transmission component 1018, and

[0184] The processor 1008 is coupled to the computer-readable medium / memory 1010. The processor 1008 is responsible for general processing, including the execution of software stored on the computer-readable medium / memory 1010. The software, when executed by the processor 1008, causes the processing system 1004 to perform the various functions described herein in connection with a server. The computer-readable medium / memory 1010 can also reside in the processing system 1004. The computer-readable medium / memory 1010 can also be used for storing data that is manipulated by the processor 1008 when executing software. The processing system 1004 can further include a communications manager 1020 and / or any number of additional components not shown in the figure. Figure 10 The components shown and / or not shown in the figure can be software modules running in the processor 1008, resident / stored in the computer-readable medium / memory 1010, one or more hardware modules coupled to the processor 1008, or some combination thereof.

[0185] In some aspects, the processing system 1004 can be a component of the UE 120 and can include the memory 282 and / or at least one of the TX MIMO processor 266, the RX processor 258, and / or the controller / processor 280. In some aspects, the apparatus 1002 for wireless communication provides means for transmitting, to a client device, a reporting configuration that indicates one or more reporting conditions, where the reporting configuration further indicates that, based at least in part on the one or more reporting conditions being satisfied, the client device is to report an update associated with a machine learning component; and means for receiving, from the client device, the update associated with the machine learning component based at least in part on determining that the one or more reporting conditions are satisfied, or failing to receive the update associated with the machine learning component to the server device based at least in part on determining that the one or more reporting conditions are not satisfied. The aforementioned means can be one or more of the aforementioned components of the processing system 1004 of the apparatus 1002 configured to perform the functions recited by the aforementioned means. As described elsewhere herein, the processing system 1004 can include the TX MIMO processor 266, the RX processor 258, and / or the controller / processor 280. In one configuration, the aforementioned means can be the TX MIMO processor 266, the RX processor 258, and / or the controller / processor 280 configured to perform the functions and / or operations recited herein.

[0186] Figure 10 are provided by way of example. Other examples can differ from what is described ​ in connection with the examples described in this disclosure.

[0187] An overview of some aspects of the present disclosure is provided below:

[0188] Aspect 1 : A method of wireless communication performed by a client device, comprising: receiving a reporting configuration that indicates one or more reporting conditions, where the reporting configuration further indicates that, based at least in part on the one or more reporting conditions being satisfied, the client device is to report an update associated with a machine learning component; and transmitting, to a server device, the update associated with the machine learning component based at least in part on determining that the one or more reporting conditions are satisfied, or refraining from transmitting the update associated with the machine learning component to the server device based at least in part on the one or more reporting conditions not being satisfied.

[0189] Aspect 2: The method of aspect 1, wherein the machine learning component comprises at least one neural network.

[0190] Aspect 3: The method of aspect 1 or aspect 2, wherein the one or more reporting conditions correspond to an amount of training data collected by the client device.

[0191] Aspect 4: The method of any of aspects 1-3, wherein the one or more reporting conditions comprise a data volume threshold, and the method further comprises: determining an amount of training data collected by the client device during the collection period; and determining that the amount of training data collected by the client device satisfies the data volume threshold, wherein transmitting the update comprises transmitting the update based at least in part on determining that the amount of training data collected by the client device satisfies the data volume threshold.

[0192] Aspect 5: The method of aspect 4, further comprising: training the machine learning component based at least in part on determining that the amount of training data collected by the client device satisfies the data volume threshold.

[0193] Aspect 6: The method of any of aspects 1-5, wherein the one or more reporting conditions correspond to a performance of the machine learning component.

[0194] Aspect 7: The method of any of aspects 1-6, wherein the one or more reporting conditions correspond to a loss function value of the machine learning component.

[0195] Aspect 8: The method of aspects 1-7, wherein the one or more reporting conditions correspond to a loss function difference, wherein the loss function difference comprises a difference between a first loss function value associated with the machine learning component and a second loss function value associated with the machine learning component.

[0196] Aspect 9: The method of aspect 8, wherein the first loss function value corresponds to an initial instance of the machine learning component, and wherein the second loss function value corresponds to an updated instance of the machine learning component.

[0197] Aspect 10: The method of aspect 9, further comprising: receiving initial machine learning component information; and determining the initial instance of the machine learning component based at least in part on the initial machine learning component information.

[0198] Aspect 11: The method of aspect 9 or aspect 10, further comprising: determining the first loss function value; determining the second loss function value; determining the loss function difference; and determining that the loss function difference satisfies a reporting condition, wherein transmitting the update comprises transmitting the update based at least in part on determining that the loss function difference satisfies the loss function difference threshold.

[0199] Aspect 12: The method of any of aspects 1-11, wherein the one or more reporting conditions correspond to a use case associated with the machine learning component.

[0200] Aspect 13: The method of aspect 12, wherein the use case comprises at least one of: channel state information derivation, positioning measurement derivation, demodulation of a data channel, decoding of a data channel, or a combination thereof.

[0201] Aspect 14: The method of any of aspects 1-13, wherein the one or more reporting conditions correspond to a data type associated with the set of collected data.

[0202] Aspect 15: The method of aspect 14, wherein the data type comprises identically and independently distributed data, wherein transmitting the update is based at least in part on determining that the set of collected data comprises identically and independently distributed data.

[0203] Aspect 16: The method of any of aspects 1-15, wherein the reporting configuration indicates at least one communication resource to be used for reporting the update.

[0204] Aspect 17: The method of aspect 16, wherein the at least one communication resource comprises at least one of a time resource or a frequency resource.

[0205] Aspect 18: The method of any of aspects 1-17, further comprising transmitting, to the server device, an indication that the client device is refraining from transmitting the update.

[0206] Aspect 19: The method of aspect 18, wherein transmitting the update to the server device comprises transmitting a first type of report, and wherein transmitting the indication to the server device that the client device is refraining from transmitting the update comprises transmitting a second type of report.

[0207] Aspect 20: The method of aspect 19, wherein the second type of report indicates a reporting delay.

[0208] Aspect 21: The method of aspect 20, wherein the reporting delay comprises at least one time resource or frequency resource during which the client device will refrain from reporting additional updates.

[0209] Aspect 22: The method of any of aspects 19-21, wherein the second type of report indicates a current instance of the machine learning component.

[0210] Aspect 23: The method of any of aspects 19-22, wherein the second type of report indicates at least one of a loss function value associated with a training data set or a loss function value associated with a validation data set.

[0211] Aspect 24: The method of any of aspects 1-23, wherein the client device comprises a user equipment, and wherein the server device comprises a base station.

[0212] Aspect 25: A method of wireless communication performed by a server device, comprising: transmitting, to a client device, a reporting configuration that indicates one or more reporting conditions, wherein the reporting configuration further indicates that, based at least in part on the one or more reporting conditions being satisfied, the client device is to report an update associated with a machine learning component; and receiving, from the client device, the update associated with the machine learning component based at least in part on the one or more reporting conditions being satisfied, or failing to receive the update associated with the machine learning component to the server device based at least in part on determining that the one or more reporting conditions are not satisfied.

[0213] Aspect 26: The method of aspect 25, wherein the machine learning component comprises at least one neural network.

[0214] Aspect 27: The method of aspect 25 or aspect 26, wherein the one or more reporting conditions correspond to an amount of training data collected by the client device.

[0215] Aspect 28: The method of aspect 27, wherein the one or more reporting conditions comprise a data amount threshold, wherein receiving the update comprises receiving the update based at least in part on determining that the amount of training data collected by the client device satisfies the data amount threshold.

[0216] Aspect 29: The method of aspect 28, wherein the reporting configuration comprises an indication to train the machine learning component based at least in part on determining that the amount of training data collected by the client device satisfies the data amount threshold.

[0217] Aspect 30: The method of any of aspects 25-29, wherein the one or more reporting conditions correspond to a performance of the machine learning component.

[0218] Aspect 31: The method of any of aspects 25-30, wherein the one or more reporting conditions correspond to a loss function value of the machine learning component.

[0219] Aspect 32: The method of any of aspects 25-31, wherein the one or more reporting conditions correspond to a loss function difference, wherein the loss function difference comprises a difference between a first loss function value associated with the machine learning component and a second loss function value associated with the machine learning component.

[0220] Aspect 33: The method of aspect 32, wherein the first loss function value corresponds to an initial instance of the machine learning component, and wherein the second loss function value corresponds to an updated instance of the machine learning component.

[0221] Aspect 34: The method of any of aspects 32 or 34, wherein receiving the update comprises receiving the update based at least in part on the loss function difference satisfying a loss function difference threshold.

[0222] Aspect 35: The method of any of aspects 25-34, wherein the one or more reporting conditions correspond to a use case associated with the machine learning component.

[0223] Aspect 36: The method of aspect 35, wherein the use case comprises at least one of: channel state information derivation, positioning measurement derivation, demodulation of a data channel, decoding of a data channel, or a combination thereof.

[0224] Aspect 37: The method of any of aspects 25-36, wherein the one or more reporting conditions correspond to a data type associated with the set of collected data.

[0225] Aspect 38: The method of aspect 37, wherein the data type comprises identically and independently distributed data, wherein receiving the update is based at least in part on determining that the set of collected data comprises identically and independently distributed data.

[0226] Aspect 39: The method of any of aspects 25-38, wherein the reporting configuration indicates at least one communication resource to be used for reporting the update.

[0227] Aspect 40: The method of aspect 39, wherein the at least one communication resource comprises at least one of a time resource or a frequency resource.

[0228] Aspect 41: The method of any of aspects 25-40, further comprising determining that the update is not received from the client device.

[0229] Aspect 42: The method of aspect 41, wherein determining that the update is not received from the client device comprises performing a blind detection procedure.

[0230] Aspect 43: The method of aspect 41 or 42, wherein determining that the update is not received from the client device comprises receiving an indication from the client device that the client device is refraining from sending the update.

[0231] Aspect 44: The method of aspect 43, wherein receiving the update from the client device comprises receiving a first type of report, and wherein receiving the indication from the client device that the client device is refraining from sending the update comprises receiving a second type of report.

[0232] Aspect 45: The method of aspect 44, wherein the second type of report indicates a reporting delay.

[0233] Aspect 46: The method of aspect 45, wherein the reporting delay comprises at least one time resource or frequency resource during which the client device will refrain from reporting additional updates.

[0234] Aspect 47: The method of any of aspects 44-Aspect 46, wherein the second type of report indicates a current instance of the machine learning component.

[0235] Aspect 48: The method of any of aspects 44-Aspect 47, wherein the second type of report indicates at least one of a loss function value associated with a training data set or a loss function value associated with a validation data set.

[0236] Aspect 49: The method of any of aspects 25-Aspect 48, wherein the client device comprises a user equipment, and wherein the server device comprises a base station.

[0237] Aspect 50: An apparatus for wireless communication at a device, comprising a processor; memory coupled with the processor; and instructions stored in the memory and executable by the processor to cause the apparatus to perform the method of one or more of aspects 1-24.

[0238] Aspect 51: A device for wireless communication, comprising a memory and one or more processors coupled to the memory, the one or more processors configured to perform the method of one or more of aspects 1-24.

[0239] Aspect 52: A device for wireless communication, comprising at least one means for performing the method of one or more of aspects 1-24.

[0240] Aspect 53: A non-transitory computer-readable medium storing code for wireless communication, the code comprising instructions executable by a processor to perform the method of one or more of aspects 1-24.

[0241] Aspect 54: A non-transitory computer-readable medium storing a set of instructions for wireless communication, the set of instructions comprising one or more instructions that, when executed by one or more processors of a device, cause the device to perform the method of one or more of aspects 1-24.

[0242] Aspect 55: An apparatus for wireless communication at a device, comprising a processor; memory coupled with the processor; and instructions stored in the memory and executable by the processor to cause the apparatus to perform the method of one or more of aspects 25-49.

[0243] Aspect 56: An apparatus for wireless communication, comprising a memory and one or more processors coupled to the memory, the one or more processors configured to perform the method of one or more of Aspects 25-49.

[0244] Aspect 57: An apparatus for wireless communication, comprising at least one means for performing the method of one or more of Aspects 25-49.

[0245] Aspect 58: A non-transitory computer-readable medium storing code for wireless communication, the code comprising instructions executable by a processor to perform the method of one or more of Aspects 25-49.

[0246] Aspect 59: A non-transitory computer-readable medium storing a set of instructions for wireless communication, the set of instructions comprising one or more instructions that, when executed by one or more processors of an apparatus, cause the apparatus to perform the method of one or more of Aspects 25-49.

[0247] The above disclosure provides illustration and description, but is not intended to be exhaustive or to limit the aspects to the precise form disclosed. Modifications and variations can be possible based on the above disclosure or from practice of the aspects.

[0248] As used herein, the term “component” is intended to be broadly interpreted to include hardware, firmware, and / or combinations of hardware and software. As used herein, a processor is implemented in hardware, firmware, and / or combinations of hardware and software. It will be apparent that systems and / or methods described herein can be implemented in different forms of hardware, firmware, and / or a combination of hardware and software. The actual specialized control hardware or software code used to implement these systems and / or methods is not limiting of the aspects. Thus, the operation and behavior of the systems and / or methods were described herein without reference to specific software code — it being understood that software and hardware can be designed to implement the systems and / or methods based, at least in part, on the description herein.

[0249] As used herein, depending on the context, meeting a threshold can refer to a value being greater than the threshold, greater than or equal to the threshold, less than the threshold, less than or equal to the threshold, equal to the threshold, not equal to the threshold, etc.

[0250] Although specific combinations of features are recited 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 ways not specifically recited in the claims and / or disclosed in the specification. Although each dependent claim listed below can stand on its own as a separate embodiment, the disclosure of the various aspects includes all possible combinations of the dependent claims with the independent claims. As used in this document, the phrase“at least one of” followed by a list of items means any combination of those items (including single members). For example,“at least one of a, b, or c” means“a” or“b” or“c” or“a-b” or“a-c” or“b-c” or“a-b-c” or any combination of these items with multiples of oneself. Although specific embodiments have been illustrated and described herein, it will be appreciated that various modifications and changes can be made without departing from the spirit and scope of the application. Accordingly, it is intended that all such modifications and changes be considered as within the scope of the application. The following clauses are intended to be included within the scope of the application.

[0251] No element, act, or instruction used herein should be construed as critical or essential unless explicitly described as such. Also, as used herein, the articles“a” and“an” are intended to include one or more items, and can be used interchangeably with“one or more.” Furthermore, as used herein, the article“the” is intended to include one or more items unless otherwise indicated by context. Also, as used herein, the terms“set” and“group” are intended to include one or more items (for example, related items, unrelated items, or a combination of related and unrelated items), and can be used interchangeably with“one or more.” Where only one item is intended, the phrase“only one” or similar language is used. Also, as used herein, the terms“has,”“have,”“having,” or the like are intended to be open-ended terms. Further, the phrase“based on” is intended to mean“based, at least in part, on” unless explicitly stated otherwise. Also, as used herein, the term“or” is intended to be inclusive when used in a series and can be used interchangeably with“and / or,” unless explicitly stated otherwise (e.g., if used in combination with“either” or“only one of”).

Claims

1. A client device for wireless communication, comprising: a memory; and one or more processors, coupled to the memory, configured to: receive, from a server device, a reporting configuration that indicates one or more reporting conditions, wherein the reporting configuration further indicates that, based at least in part on the one or more reporting conditions being satisfied, the client device is to report an update associated with a machine learning component; and selectively transmit, to the server device, the update associated with the machine learning component based at least in part on whether the one or more reporting conditions are satisfied, wherein the one or more processors, to selectively transmit, to the server device, the update associated with the machine learning component, are configured to: transmit, to the server device, the update associated with the machine learning component based at least in part on the one or more reporting conditions being satisfied, or inhibit transmitting, to the server device, the update associated with the machine learning component based at least in part on the one or more reporting conditions not being satisfied. the one or more reporting conditions correspond to an amount of training data collected by the client device.

2. The client device of claim 1, wherein, the one or more reporting conditions include a data amount threshold, and wherein the one or more processors are further configured to:

3. The client device of claim 1, wherein, determine an amount of training data collected by the client device during a collection period; and determine that the amount of training data collected by the client device satisfies the data amount threshold, wherein the one or more processors, to transmit the update, are configured to transmit the update based at least in part on the amount of training data collected by the client device satisfying the data amount threshold. the one or more processors are further configured to:

4. The client device of claim 3, wherein, train the machine learning component based at least in part on the amount of training data collected by the client device satisfying the data amount threshold. the one or more reporting conditions correspond to a performance of the machine learning component.

5. The client device of claim 1, wherein, the one or more reporting conditions correspond to a loss function value of the machine learning component.

6. The client device of claim 1, wherein, the one or more reporting conditions correspond to a loss function difference, wherein the loss function difference comprises a difference between a first loss function value associated with the machine learning component and a second loss function value associated with the machine learning component.

7. The client device of claim 1, wherein, the first loss function value corresponds to an initial instance of the machine learning component, and wherein the second loss function value corresponds to an updated instance of the machine learning component.

8. The client device of claim 7, wherein, the one or more processors are further configured to:

9. The client device of claim 8, wherein, receive initial machine learning component information; and determine the initial instance of the machine learning component based at least in part on the initial machine learning component information. the one or more processors are further configured to:

10. The client device of claim 9, wherein, determine the first loss function value; determine the second loss function value; determine the loss function difference; and determine that the loss function difference satisfies the one or more reporting conditions, ​ ​ wherein the one or more processors, to transmit the update, are configured to transmit the update based at least in part on the loss function difference satisfying a loss function difference threshold.

11. The client device of claim 1, wherein, The one or more reporting conditions correspond to a use case associated with the machine learning component.

12. The client device of claim 11, wherein, The use case includes at least one of: channel state information derivation, positioning measurement derivation, demodulation of a data channel, decoding of a data channel, or a combination thereof.

13. The client device of claim 1, wherein, The one or more reporting conditions correspond to a data type associated with a set of collected data.

14. The client device of claim 13, wherein, The data type includes identically and independently distributed data, wherein the one or more processors, to transmit the update, are configured to transmit the update based at least in part on a determination that the set of collected data includes identically and independently distributed data.

15. The client device of claim 1, wherein, The report configuration indicates at least one communication resource to be used for reporting the update.

16. The client device of claim 15, wherein, The at least one communication resource includes at least one of a time resource or a frequency resource.

17. The client device of claim 1, wherein, The one or more processors are further configured to transmit, to the server device, an indication that the client device is refraining from transmitting the update.

18. The client device of claim 17, wherein, The one or more processors, to transmit the update to the server device, are configured to transmit a first type of report, and wherein the one or more processors, to transmit the indication to the server device that the client device is refraining from transmitting the update, are configured to transmit a second type of report.

19. The client device of claim 18, wherein, The second type of report indicates a reporting delay.

20. The client device of claim 19, wherein, The reporting delay includes at least one time resource or frequency resource during which the client device will refrain from reporting additional updates.

21. The client device of claim 18, wherein, The second type of report indicates a current instance of the machine learning component.

22. The client device of claim 18, wherein, The second type of report indicates at least one of a loss function value associated with a set of training data or a loss function value associated with a set of validation data.

23. The client device of claim 1, wherein, The client device includes a user equipment, and wherein the server device includes a base station.

24. The client device of claim 1, wherein, The one or more reporting conditions are associated with the machine learning component.

25. A server device for wireless communication, comprising: a memory; and one or more processors, coupled to the memory, configured to: transmit, to a client device, a report configuration indicating one or more reporting conditions, wherein the report configuration further indicates that the client device is to report an update associated with a machine learning component based at least in part on the one or more reporting conditions being satisfied; and receive, from the client device, the update associated with the machine learning component based at least in part on the one or more reporting conditions being satisfied, wherein the update associated with the machine learning component is refrained from being transmitted by the client device based at least in part on the one or more reporting conditions not being satisfied. The one or more reporting conditions correspond to at least one of:

26. The server device of claim 25, wherein, an amount of training data collected by the client device, a performance of the machine learning component, a loss function value of the machine learning component, a combination thereof. a use case associated with the machine learning component, or a data type associated with a set of collected data.

27. The server device of claim 25, wherein, The report configuration indicates at least one communication resource to be used for reporting the update.

28. The server device of claim 25, wherein, The one or more reporting conditions are associated with the machine learning component.

29. A method of wireless communication performed by a client device, comprising: receiving, from a server device, a report configuration indicating one or more reporting conditions, wherein the report configuration further indicates that, based at least in part on the one or more reporting conditions being satisfied, the client device is to report an update associated with a machine learning component; and selectively transmitting, to the server device, the update associated with the machine learning component based at least in part on whether the one or more reporting conditions are satisfied, wherein the update associated with the machine learning component is transmitted to the server device based at least in part on the one or more reporting conditions being satisfied, or wherein the update associated with the machine learning component is not transmitted to the server device based at least in part on the one or more reporting conditions not being satisfied.

30. The method of claim 29, wherein, The one or more reporting conditions comprise a data volume threshold, the method further comprising: determining an amount of training data collected by the client device during a collection period; and determining that the amount of training data collected by the client device satisfies the data volume threshold, wherein transmitting the update comprises transmitting the update based at least in part on determining that the amount of training data collected by the client device satisfies the data volume threshold.

31. The method of claim 29, wherein, The one or more reporting conditions correspond to a loss function difference, wherein the loss function difference comprises a difference between a first loss function value associated with the machine learning component and a second loss function value associated with the machine learning component.

32. The method of claim 29, wherein, The one or more reporting conditions are associated with the machine learning component.

33. A method of wireless communication performed by a server device, comprising: transmitting, to a client device, a report configuration indicating one or more reporting conditions, wherein the report configuration further indicates that, based at least in part on the one or more reporting conditions being satisfied, the client device is to report an update associated with a machine learning component; and receiving, from the client device, the update associated with the machine learning component based at least in part on the one or more reporting conditions being satisfied, wherein the update associated with the machine learning component is suppressed from being transmitted by the client device based at least in part on the one or more reporting conditions not being satisfied.

34. The method of claim 33, wherein, The one or more reporting conditions are associated with the machine learning component.

Images