Vertical federated learning in a wireless communication system

Abstract

Various aspects of the present disclosure relate to a first network entity for wireless communication. The first network entity may be configured to, capable of, or operable to receive, from a second network entity, a registration request to register the second network entity for participating in a vertical federated learning, VFL, operation, wherein the registration request comprises an indication of a VFL capability of the second network entity; and transmit, to the second network entity, a registration response.

Description

VERTICAL FEDERATED LEARNING IN A WIRELESS COMMUNICATION SYSTEMTECHNICAL FIELD

[0001] The present disclosure relates generally to wireless communication, including the Vertical Federated Learning (VFL).BACKGROUND

[0002] A wireless communications system may include one or multiple network communication devices, which may be otherwise knowns as network equipment (NE) supporting wireless communications for one or multiple user communication devices, which may be otherwise known as user equipment (UE), or other suitable terminology. The wireless communications system may support wireless communications with one or multiple user communication devices by utilizing resources of the wireless communication system (e.g., time resources (e.g., symbols, slots, subframes, frames, or the like) or frequency resources (e.g., subcarriers, carriers, or the like)). Additionally, the wireless communications system may support wireless communications across various radio access technologies including third generation (3G) radio access technology, fourth generation (4G) radio access technology, fifth generation (5G) radio access technology, among other suitable radio access technologies beyond 5G (e.g., sixth generation (6G)).SUMMARY

[0003] As used herein, including in the claims, an article “a” before an element is unrestricted and understood to refer to “at least one” of those elements or “one or more” of those elements. The terms “a,” “at least one,” “one or more,” and “at least one of one or more” may be interchangeable. As used herein, including in the claims, “or” as used in a list of items (e.g., a list of items prefaced by a phrase such as “at least one of’ or “one or more of’ or “one or both of’) indicates an inclusive list such that, for example, a list of at least one of A, B, or C means A or B or C or AB or AC or BC or ABC (i.e., A and B and C). Also, as used herein, including in the claims, the phrase “based on” shall not be construed as a reference to a closed set of conditions. For example, an example step that is Docket No. SMM920250161-GR-NPdescribed as “based on condition A” may be based on both a condition A and a condition B without departing from the scope of the present disclosure. In other words, as used herein, the phrase “based on” shall be construed in the same manner as the phrase “based at least in part on. Further, as used herein, including in the claims, a “set” may include one or more elements.

[0004] A first network entity for wireless communication is described. The first network entity may be configured to, capable of, or operable to perform one or more operations as described herein. For example, the first network entity may include at least one memory, and at least one processor coupled with the at least one memory and configured to cause the first network entity to: receive, from a second network entity, a registration request to register the second network entity for participating in a VFL operation, wherein the registration request comprises an indication of a VFL capability of the second network entity; and transmit, to the second network entity, a registration response.

[0005] A method performed or performable by the first network entity is described herein. The method may comprise: receiving, from a second network entity, a registration request to register the second network entity for participating in a VFL operation, wherein the registration request comprises an indication of a VFL capability of the second network entity; and transmitting, to the second network entity, a registration response.

[0006] A processor for wireless communication is described. The processor may be configured to, capable of, or operable to perform one or more operations as described herein. For example, the processor may comprise at least one controller coupled with at least one memory and configured to cause the processor to: receive, from a second network entity, a registration request to register the second network entity for participating in a VFL operation, wherein the registration request comprises an indication of a VFL capability of the second network entity; and transmit, to the second network entity, a registration response.

[0007] A second network entity for wireless communication is described. The second network entity may be configured to, capable of, or operable to perform one or more operations as described herein. For example, the second network entity may include at least Docket No. SMM920250161-GR-NPone memory, and at least one processor coupled with the at least one memory and configured to cause the second network entity to: transmit, to a first network entity, a registration request to register the second network entity for participating in a VFL operation, wherein the registration request comprises an indication of a VFL capability of the second network entity; and receive, from the second network entity, a registration response.

[0008] A method performed or performable by the second network entity is described herein. The method may comprise: transmitting, to a first network entity, a registration request to register the second network entity for participating in a VFL operation, wherein the registration request comprises an indication of a VFL capability of the second network entity; and receiving, from the second network entity, a registration response.

[0009] A processor for wireless communication is described. The processor may be configured to, capable of, or operable to perform one or more operations as described herein. For example, the processor may comprise at least one controller coupled with at least one memory and configured to cause the processor to: transmit, to a first network entity, a registration request to register the second network entity for participating in a VFL operation, wherein the registration request comprises an indication of a VFL capability of the second network entity; and receive, from the second network entity, a registration response.BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 illustrates an example of a wireless communications system in accordance with aspects of the present disclosure.

[0011] Figure 2 illustrates an on-network Artificial Intelligence (AI) / Machine Learning (ML) Enablement (AIMLE) functional model in accordance with aspects of the present disclosure.

[0012] Figure 3 illustrates a ML model lifecycle enablement in accordance with aspects of the present disclosure.Docket No. SMM920250161-GR-NP

[0013] Figure 4 illustrates various models for supporting VFL in accordance with aspects of the present disclosure.

[0014] Figure 5 illustrates non-split VFL with a coordinator in accordance with aspects of the present disclosure.

[0015] Figure 6 illustrates non-split VFL without a coordinator in accordance with aspects of the present disclosure.

[0016] Figure 7 illustrates split VFL in accordance with aspects of the present disclosure.

[0017] Figure 8 illustrates an example of a process flow for registration on an FL member registry in accordance with aspects of the present disclosure.

[0018] Figure 9 illustrates an example of a process flow for discovery of a VFL member in accordance with aspects of the present disclosure.

[0019] Figure 10 illustrates an example of a UE in accordance with aspects of the present disclosure.

[0020] Figure 11 illustrates an example of a processor in accordance with aspects of the present disclosure.

[0021] Figure 12 illustrates an example of a NE in accordance with aspects of the present disclosure.

[0022] Figure 13 illustrates a flowchart of a method performed by a NE in accordance with aspects of the present disclosure.

[0023] Figure 14 illustrates a flowchart of a method performed by a NE in accordance with aspects of the present disclosure.DETAILED DESCRIPTION

[0024] A wireless communication system, including one or more UE and NE may perform VFL. VFL is a collaborative machine learning approach where multiple parties, each holding different features about the same set of entities, jointly train a model without sharing raw data. Under the coordination of an FL Coordinator, participants (e.g., VFL Docket No. SMM920250161-GR-NPparticipants, VFL entities, VFL members) align common entity identifiers, compute local model updates using their own data, and securely exchange encrypted intermediate results or gradients. The coordinator aggregates these updates to refine a global model, which is then shared back with participants. VFL enables organizations such as operators, enterprises, or service providers to leverage complementary datasets while preserving privacy, often supported by secure computation and encryption techniques.

[0025] VFL entities may include AIMLE servers or Vertical Application Layer (VAL) servers which may have different capabilities. One or more aspects of the present disclosure provides for improvement of integration of VFL entities for performing VFL operations. Examples described herein generally relates to an improved method of registering and discovery VFL entities for VFL operations.

[0026] Aspects of the present disclosure are described in the context of a wireless communications system.

[0027] Figure 1 illustrates an example of a wireless communications system 100 in accordance with aspects of the present disclosure. The wireless communications system 100 may include one or more NE 102, one or more UE 104, and a core network (CN) 106. The wireless communications system 100 may support various radio access technologies. In some implementations, the wireless communications system 100 may be a 4G network, such as an LTE network or an LTE- Advanced (LTE-A) network. In some other implementations, the wireless communications system 100 may be a NR network, such as a 5G network, a 5G-Advanced (5G-A) network, or a 5G ultrawideband (5G-UWB) network. In other implementations, the wireless communications system 100 may be a combination of a 4G network and a 5G network, or other suitable radio access technology including Institute of Electrical and Electronics Engineers (IEEE) 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), IEEE 802.20. The wireless communications system 100 may support radio access technologies beyond 5G, for example, 6G. Additionally, the wireless communications system 100 may support technologies, such as time division multiple access (TDMA), frequency division multiple access (FDMA), or code division multiple access (CDMA), etc.Docket No. SMM920250161-GR-NP

[0028] The one or more NE 102 may be dispersed throughout a geographic region to form the wireless communications system 100. One or more of the NE 102 described herein may be or include or may be referred to as a network node, a base station, a network element, a network function, a network entity, a radio access network (RAN), a NodeB, an eNodeB (eNB), a next-generation NodeB (gNB), or other suitable terminology. An NE 102 and a UE 104 may communicate via a communication link, which may be a wireless or wired connection. For example, an NE 102 and a UE 104 may perform wireless communication (e.g., receive signalling, transmit signalling) over a Uu interface.

[0029] An NE 102 may provide a geographic coverage area for which the NE 102 may support services for one or more UEs 104 within the geographic coverage area. For example, an NE 102 and a UE 104 may support wireless communication of signals related to services (e.g., voice, video, packet data, messaging, broadcast, etc.) according to one or multiple radio access technologies. In some implementations, an NE 102 may be moveable, for example, a satellite associated with a non-terrestrial network (NTN). In some implementations, different geographic coverage areas associated with the same or different radio access technologies may overlap, but the different geographic coverage areas may be associated with different NE 102.

[0030] The one or more UE 104 may be dispersed throughout a geographic region of the wireless communications system 100. A UE 104 may include or may be referred to as a remote unit, a mobile device, a wireless device, a remote device, a subscriber device, a transmitter device, a receiver device, or some other suitable terminology. In some implementations, the UE 104 may be referred to as a unit, a station, a terminal, or a client, among other examples. Additionally, or alternatively, the UE 104 may be referred to as an Internet-of-Things (loT) device, an Internet-of-Everything (loE) device, or machine-type communication (MTC) device, among other examples.

[0031] A UE 104 may be able to support wireless communication directly with other UEs 104 over a communication link. For example, a UE 104 may support wireless communication directly with another UE 104 over a device-to-device (D2D) communication link. In some implementations, such as vehi cl e-to- vehicle (V2V) deployments, vehicle-to-everything (V2X) deployments, or cellular-V2X deployments, theDocket No. SMM920250161-GR-NPcommunication link may be referred to as a sidelink. For example, a UE 104 may support wireless communication directly with another UE 104 over a PC5 interface.

[0032] An NE 102 may support communications with the CN 106, or with another NE 102, or both. For example, an NE 102 may interface with other NE 102 or the CN 106 through one or more backhaul links (e.g., SI, N2, N2, or network interface). In some implementations, the NE 102 may communicate with each other directly. In some other implementations, the NE 102 may communicate with each other or indirectly (e.g., via the CN 106. In some implementations, one or more NE 102 may include subcomponents, such as an access network entity, which may be an example of an access node controller (ANC). An ANC may communicate with the one or more UEs 104 through one or more other access network transmission entities, which may be referred to as a radio heads, smart radio heads, or transmission-reception points (TRPs).

[0033] The CN 106 may support user authentication, access authorization, tracking, connectivity, and other access, routing, or mobility functions. The CN 106 may be an evolved packet core (EPC), or a 5G core (5GC), which may include a control plane entity that manages access and mobility (e.g., a mobility management entity (MME), an access and mobility management functions (AMF)) and a user plane entity that routes packets or interconnects to external networks (e.g., a serving gateway (S-GW), a Packet Data Network (PDN) gateway (P-GW), or a user plane function (UPF)). In some implementations, the control plane entity may manage non-access stratum (NAS) functions, such as mobility, authentication, and bearer management (e.g., data bearers, signal bearers, etc.) for the one or more UEs 104 served by the one or more NE 102 associated with the CN 106.

[0034] The CN 106 may communicate with a packet data network over one or more backhaul links (e.g., via an SI, N2, N2, or another network interface). The packet data network may include an application server. In some implementations, one or more UEs 104 may communicate with the application server. A UE 104 may establish a session (e.g., a protocol data unit (PDU) session, or the like) with the CN 106 via an NE 102. The CN 106 may route traffic (e.g., control information, data, and the like) between the UE 104 and the application server using the established session (e.g., the established PDU session). TheDocket No. SMM920250161-GR-NPPDU session may be an example of a logical connection between the UE 104 and the CN 106 (e.g., one or more network functions of the CN 106).

[0035] In the wireless communications system 100, the NEs 102 and the UEs 104 may use resources of the wireless communications system 100 (e.g., time resources (e.g., symbols, slots, subframes, frames, or the like) or frequency resources (e.g., subcarriers, carriers)) to perform various operations (e.g., wireless communications). In some implementations, the NEs 102 and the UEs 104 may support different resource structures. For example, the NEs 102 and the UEs 104 may support different frame structures. In some implementations, such as in 4G, the NEs 102 and the UEs 104 may support a single frame structure. In some other implementations, such as in 5G and among other suitable radio access technologies, the NEs 102 and the UEs 104 may support various frame structures (i.e., multiple frame structures). The NEs 102 and the UEs 104 may support various frame structures based on one or more numerologies.

[0036] One or more numerologies may be supported in the wireless communications system 100, and a numerology may include a subcarrier spacing and a cyclic prefix. A first numerology (e.g., / t=0) may be associated with a first subcarrier spacing (e.g., 15 kHz) and a normal cyclic prefix. In some implementations, the first numerology (e.g., / t=0) associated with the first subcarrier spacing (e.g., 15 kHz) may utilize one slot per subframe. A second numerology (e.g., / / =1) may be associated with a second subcarrier spacing (e.g., 30 kHz) and a normal cyclic prefix. A third numerology (e.g., g=2) may be associated with a third subcarrier spacing (e.g., 60 kHz) and a normal cyclic prefix or an extended cyclic prefix. A fourth numerology (e.g., / t=3) may be associated with a fourth subcarrier spacing (e.g., 120 kHz) and a normal cyclic prefix. A fifth numerology (e.g., / t=4) may be associated with a fifth subcarrier spacing (e.g., 240 kHz) and a normal cyclic prefix.

[0037] A time interval of a resource (e.g., a communication resource) may be organized according to frames (also referred to as radio frames). Each frame may have a duration, for example, a 10 millisecond (ms) duration. In some implementations, each frame may include multiple subframes. For example, each frame may include 10 subframes, and each subframe may have a duration, for example, a 1 ms duration. In some implementations,Docket No. SMM920250161-GR-NPeach frame may have the same duration. In some implementations, each subframe of a frame may have the same duration.

[0038] Additionally or alternatively, a time interval of a resource (e.g., a communication resource) may be organized according to slots. For example, a subframe may include a number (e.g., quantity) of slots. The number of slots in each subframe may also depend on the one or more numerologies supported in the wireless communications system 100. For instance, the first, second, third, fourth, and fifth numerologies (i.e., / t=0, / t=l, =2, jtz=3, =4) associated with respective subcarrier spacings of 15 kHz, 30 kHz, 60 kHz, 120 kHz, and 240 kHz may utilize a single slot per subframe, two slots per subframe, four slots per subframe, eight slots per subframe, and 16 slots per subframe, respectively. Each slot may include a number (e.g., quantity) of symbols (e.g., OFDM symbols). In some implementations, the number (e.g., quantity) of slots for a subframe may depend on a numerology. For a normal cyclic prefix, a slot may include 14 symbols. For an extended cyclic prefix (e.g., applicable for 60 kHz subcarrier spacing), a slot may include 12 symbols. The relationship between the number of symbols per slot, the number of slots per subframe, and the number of slots per frame for a normal cyclic prefix and an extended cyclic prefix may depend on a numerology. It should be understood that reference to a first numerology (e.g., / t=0) associated with a first subcarrier spacing (e.g., 15 kHz) may be used interchangeably between subframes and slots.

[0039] In the wireless communications system 100, an electromagnetic (EM) spectrum may be split, based on frequency or wavelength, into various classes, frequency bands, frequency channels, etc. By way of example, the wireless communications system 100 may support one or multiple operating frequency bands, such as frequency range designations FR1 (410 MHz - 7.125 GHz), FR2 (24.25 GHz - 52.6 GHz), FR3 (7.125 GHz - 24.25 GHz), FR4 (52.6 GHz - 114.25 GHz), FR4a or FR4-1 (52.6 GHz - 71 GHz), and FR5 (114.25 GHz - 300 GHz). In some implementations, the NEs 102 and the UEs 104 may perform wireless communications over one or more of the operating frequency bands. In some implementations, FR1 may be used by the NEs 102 and the UEs 104, among other equipment or devices for cellular communications traffic (e.g., control information, data).Docket No. SMM920250161-GR-NPIn some implementations, FR2 may be used by the NEs 102 and the UEs 104, among other equipment or devices for short-range, high data rate capabilities.

[0040] FR1 may be associated with one or multiple numerol ogies (e.g., at least three numerologies). For example, FR1 may be associated with a first numerology (e.g., / t=0), which includes 15 kHz subcarrier spacing; a second numerology (e.g., / z=l), which includes 30 kHz subcarrier spacing; and a third numerology (e.g., / z=2), which includes 60 kHz subcarrier spacing. FR2 may be associated with one or multiple numerologies (e.g., at least 2 numerologies). For example, FR2 may be associated with a third numerology (e.g., =2), which includes 60 kHz subcarrier spacing; and a fourth numerology (e.g., / t=3), which includes 120 kHz subcarrier spacing.

[0041] In wireless communications systems, vertical-specific applications and edge applications may be considered as the major consumers of third Generation Partnership Project (3GPP)-provided data analytics and AI / ML support services. In such cases, AIMLE service may play a role on the exposure of AI / ML services from different 3 GPP domains to the vertical / Application Service Provider (ASP) in a unified manner on top of 3 GPP core network and Operations, Administration, and Maintenance (0AM); and on defining, at a Service Enabler Architecture Layer (SEAL) layer, value-add support services for assisting AI / ML services provided by the VAL layer, while being complementary to AI / ML support solutions provided in other 3GPP domains.

[0042] In some examples described herein, a first NE 102 may receive, from a second NE 102, a registration request to register the second NE 102 for participating in a VFL operation. The registration request may comprise an indication of a VFL capability of the second NE 102. The first NE 102 may transmit, to the second NE 102, a registration response.

[0043] Figure 2 is a diagram 200 illustrating an example of an on-network functional model of AIML enablement in accordance with aspects of the present disclosure. The diagram 200 comprises a UE 205, a 3GPP Network System 240, a VAL server(s) 216, ML Repository 241 and an AIMLE server 236. The UE 205 comprises a VAL 210 and a SEAL 220. The VAL 210 comprises a VAL client(s) 212. The SEAL 220 comprises an AIML-C 230 and an AIMLE client 232. The VAL server(s) 216 connects to the VAL client(s) 212 Docket No. SMM920250161-GR-NPvia a VAL-UU 214 reference point. The AIMLE client 232 connects to the AIMLE server 236 via an AIML-UU 234 reference point. The 3GPP Network System 240 connects to the AIMLE server 236 via network interfaces 235. The AIMLE server 236 connects to the VAL server(s) 216 via an AIML-S 231 reference point. The AIMLE server 236 connects to the ML Repository 241 via AIML-R 233 reference point. The AIMLE server 236 comprises an AIML-E 238 reference point.

[0044] In the VAL, the VAL client 212 communicates with the VAL server 216 over the VAL-UU 214 (e.g., VAL-UU reference point). VAL-UU 214 supports both unicast and multicast delivery modes. The AIML enablement functional entities on the UE 205 and the server are grouped into AIMLE client(s) 232 and AIML enablement server(s) 236, respectively.

[0045] The AIMLE server 236 is a SEAL server which includes of a common set of services for comprehensive enablement of AIML functionality. The AIMLE server 236 defines the following group of capabilities: support for application-layer ML model related aspects (e.g., model retrieval, model training, model monitoring, model selection, model update and model storage / discovery); assistance in AI / ML task transfer and split AI / ML operations; support Horizontal Federated Learning (HFL) / VFL operations (e.g., Federated Learning (FL) member registration, FL grouping and FL-related events notification, VFL feature alignment, HFL training); support for AIMLE client registration, discovery, participation and selection.

[0046] AIMLE client functional entity acts as the application client supporting AIMLE services. The ML repository 241 is an entity that serves as: a registry for ML / FL members (application layer entities participating in an AI / ML operation) and as a repository for application layer ML model related information.

[0047] One key role of AIMLE is applicable to ML model lifecycle enablement which provides assistance for use cases where an ASP / VAL layer aims to find and use other application entities to perform some ML operations (e.g. ML model inference) and AIMLE server 236 as a mediator to accomplish that.Docket No. SMM920250161-GR-NP

[0048] Figure 3 is a diagram 300 illustrating an example of ML model lifecycle enablement in accordance with aspects of the present disclosure. The ML model lifecycle enablement diagram 300 comprises a VAL server(s) 316 for ML model operational workflow and an AIMLE 330 for ML model lifecycle enablement. The VAL Server(s) 316 comprises data management, model training, model evaluation, model deployment and model inference. The AIMLE 330 comprises ML model related support which comprises model retrieval, model discovery and model storage. The AIMLE 330 further comprises ML operation related support which comprises VFL / HFL enablement, Transfer Learning (TL) enablement, split AI / ML operation, Data management support and FL member support e.g., grouping, register and events. The AIMLE 330 further comprises AIMLE client support which comprises AIMLE register, discovery, participate and monitoring

[0049] Diagram 300 may be an exemplary grouping of AIMLE capabilities for enablement. In particular, AIMLE 330 may undertake: ML model related support capabilities such as model retrieval, discovery and storage; ML operation related support capabilities such as VFL / HFL and TL enablement; split AI / ML operation support, data management assistance, AI / ML task transfer, FL assistance in member grouping, registration and event notification; and AIMLE client related support capabilities, including AIMLE client registration, discovery, participation, monitoring, selection.

[0050] FL is a machine learning technique that enables multiple FL clients to train a model by exchanging the parameters instead of exchanging / sharing local data set. FL servers perform management of FL operations by maintaining and updating a global ML model, selecting and managing FL clients, performing aggregation strategies, scheduling training in a federated manner, and communicating with FL clients. FL clients provide various aspects of data for FL operations, such as data collection, data preparation, and using data for training and / or inferencing while communicating updates of ML models to FL servers.

[0051] Further, Considering the fact that the FL / ML clients can be deployed on end devices like UEs, there is potentially a very large number of FL / ML clients that can participate in machine learning operations. Out of these potentially large number for FL / ML clients, a set of FL / ML clients can be selected for performing various machineDocket No. SMM920250161-GR-NPlearning tasks. Due to various factors like mobility, changing capabilities, varying resource conditions, etc, the set of UEs (e.g., hosting FL / ML clients) that can participate in federated / distributed learning changes over time and may change more frequently. Also, the model information that is exchanged between FL / ML clients and the machine learning servers could also be huge, considering the large machine learning models. So, there will be frequent need for changing the member FL / ML clients that can participate in federated / distributed machine learning operations and also frequently the need to distribute the model information.

[0052] Further, Considering the fact that the FL / ML clients can be deployed on end devices like UEs, there is potentially a very large number of FL / ML clients that can participate in machine learning operations. Out of these potentially large number for FL / ML clients, a set of FL / ML clients can be selected for performing various machine learning tasks. Due to various factors like mobility, changing capabilities, varying resource conditions, etc, the set of UEs (hosting FL / ML clients) that can participate in federated / distributed learning changes over time and may change more frequently. Also, the model information that is exchanged between FL / ML clients and the machine learning servers could also be huge, considering the large machine learning models. So, there will be frequent need for changing the member FL / ML clients that can participate in federated / distributed machine learning operations and also frequently the need to distribute the model information.

[0053] There are two capabilities (including procedures and APIs) related to the registration and events notifications related to FL members (or participants which may be FL clients). The first capability relates to support for FL member registration: This functionality covers the registration and registration update of the candidate FL member to the ML repository which is keeping the FL member registrations. Such candidate member can be a VAL server functionality or an enabler layer functionality (e.g. AIMLE server) which is registering to the ML repository / registry to act as FL member for a given application event (analytics event or event triggered by a VAL layer application server).

[0054] The second capability relates to support for FL events subscription and notification: This functionality enables a consumer (who can be the AIMLE server or aDocket No. SMM920250161-GR-NPVAL server e.g. acting as FL server) to subscribe for FL related events and getting notified on changes on the availability of the FL members which are to be used for the FL-related task (e.g., training). This capability at the ML repository acting as an AIML service registry supports the subscription for events related to FL members and the notification to the consumer in case of changes. This feature assumes that such FL members (e.g., AIMLE or VAL server or AIMLE clients) have previously registered to this registry their availability and capabilities.

[0055] There are two types of FL: HFL and VFL. HFL (or sample-based FL) is introduced in the scenarios that data sets share the same feature space but have different samples. VFL (or feature-based FL) is applicable to the cases that two data sets share the same sample space but differ in feature space.

[0056] Figure 4 is a diagram 400 illustrates various models for supporting VFL in accordance with aspects of the present disclosure. Diagram 400 relates to various models for supporting VFL. The diagram 400 illustrates that VFL algorithms 450 comprises Customized VFL 452, Split VFL 454 and Non-split VFL 456. Non-split VFL 456 comprises Non-split VFL with coordinator 458 and Non-split VFL without coordinator 459.

[0057] There are different approaches on how to train a model with a VFL algorithm 450 depending on whether non-split VFL 456 or split VFL 454. In all VFL scenarios, one party is the "label owner" or "active participant", that is, knows how to classify input data and the other parties "passive participants" or "workers" (can be multiple) participate in the VFL training process. In non-split VFL 456, passive participants send intermediate results based on data collected locally using their own model to active participants and the active participants computes gradients / losses using as basis the labels and its own ML model. Non-split VFL with coordinator 458 involves a coordinator that ensures exchange of messages between VFL parties are encrypted.

[0058] Figure 5 is a diagram 500 that illustrates non-split VFL with a coordinator in accordance with aspects of the present disclosure. Diagram 500 illustrates a party A label owner 550, a party B and a coordinator C 554. The coordinator C 554 sends public keys to party A 550 and party B 552. Party A 550 and party B 552 then exchange intermediate Docket No. SMM920250161-GR-NPresults. Party A 550 and party B 552 then send computing gradients to coordinator C 554. Coordinator C 554 then sends an updating model to party A 550 and party B 552.

[0059] Figure 6 is a diagram 600 that illustrates non-split VFL without a coordinator in accordance with aspects of the present disclosure. Diagram 600 illustrates party A label owner 650 and party B 652. Party A 650 sends public keys to party B 652. Party B 652 then sends intermediate results to party A 650. Party A 650 then sends loss to party B 652. Party B 652 then sends encrypted gradients to party A 650. Party A 650 sends decrypted gradients to party B 652. Then party A 650 and party B 652 update their models.

[0060] Figure 7 is a diagram 700 that illustrates split VFL in accordance with aspects of the present disclosure. Diagram 700 comprises party A 750, party B 752, party N 754 and server (e.g., VFL server, label owner) 756. Party A 750, party B 752 and party N 754 send intermediate results to server 756. The server 756 computes gradients. The server 756 sends gradients to party A 750, party B 752 and party N 754. Party A 750, party B 752 and party N 754 update the model.

[0061] In split VFL the model is split between several parties. One party owns the top model (e.g., label owner / VFL server 756) and other parties own one or more bottom models (e.g., passive participants). The label owner (e.g., VFL server 756) may also be the active participant. In contrast to non-split VFL 456, the VFL server 756 is aware of the labels and is able to compute gradient / losses that are shared to passive participants

[0062] VFL sample alignment across VAL servers tends to be an issue. In the VFL process, the active party or coordinating server collects partial results from other participants (e.g., passive parties) to obtain a global model. VFL participants may be VAL servers, AIMLE servers, and / or AIMLE clients. VFL participants share the same sample space but have different feature sets. Therefore, to achieve VFL process, these different VFL participants tend to require sample alignment to participate in a VFL operation. In some cases, how these samples are identified by different participants may also differ. Sample alignment allows matching corresponding data entries across different datasets in a privacy-preserving manner.Docket No. SMM920250161-GR-NP

[0063] Supporting VFL sample alignment may involve enabling the AIMLE server to support sample alignment among VFL participants, whilst preserving the privacy of the UEs, and whilst resolving the potential differences in how each VFL participant identifies the UEs. This tends to assume: the VFL participants being VAL or AIMLE servers have registered their capabilities; and the VFL server has discovered the VFL participants with the desired feature set and sample space. The AIMLE server may also assist in discovering VFL clients that match the required feature set and sample space using previously mapped UE identifiers.

[0064] Some examples described herein relate to how VFL participants being serverside entities (e.g., AIMLE or VAL servers) register their capabilities to be selected as VFL clients in an application layer VFL operation (e.g., supported by AIMLE). Some examples described herein relate to how VFL clients being server-side entities (e.g., AIMLE or VAL servers) get discovered by the VFL server in an application layer VFL operation (e.g., supported by AIMLE).

[0065] Examples described herein generally relate to a mechanism for supporting registering and discovering VFL participants of different capabilities, where these participants are AIMLE or VAL server or EAS.

[0066] Some examples described herein relate to the registration support for a FL member being a server-side entity. The registration may include information such as the sample pool and binding criteria. Some examples described herein relate to the discovery support including means of discovering different types of VFL members from the serverside. The discovery criteria information may comprise sample pool and binding criteria.

[0067] Figure 8 illustrates an example of a process flow 800 in accordance with aspects of the present disclosure. The process flow 800 may implement or be implemented by aspects of the wireless communication system 100. For example, the process flow 800 may include a candidate FL member (e.g., VAL server, AIMLE Server, second network entity) 816 and a ML repository 841 (e.g., first network entity), which may be one or more examples of devices described herein with reference to Figure 1.Docket No. SMM920250161-GR-NP

[0068] The process flow 800 may be referred to as a procedure, including one or more operations performed by one or more of the candidate FL member 816 and the ML repository 841.

[0069] In the following description of the process flow 800, the operations or signalling performed between one or more of the candidate FL member 816 and the ML repository 841 may be performed or signalled (e.g., transmitted, received) in a different order than the example order shown, or the operations or signalling performed by one or more of the candidate FL member 816 and the ML repository 841 may be performed or signalled (e.g., transmitted, received) in different orders or at different times. Some operations or signalling may also be omitted from the process flow 800. Additionally, although some operations or signalling may be shown to occur at different times, these operations or signalling may occur at the same time or in overlapping time periods. Process flow 800 relates to FL member registration. Process flow 800 illustrates the procedure where the registration or registration update of a candidate FL member happens via the ML repository, serving as AIML service registry.

[0070] Process flow 800 starts at step 871 in which the candidate FL member (e.g., VAL server via AIMLE server or AIMLE server) sends (e.g., transmits, outputs) an FL member registration (or registration update) request (e.g., registration request) to the ML repository 841 for registering to the ML repository 841 which acts as the AIML service registry. The FL member registration request may comprise an indication of a VFL capability of the candidate FL member 816 (e.g., indication of a VFL capability of the second network entity). Table 1 describes the information elements in a FL member registration request (e.g., indication of a VFL capability of the second network entity). Table 2 describes the information elements in a FL member registration update request (e.g., indication of a VFL capability of the second network entity).

[0071] In step 872, the ML repository 841 validates the received request and generates the identity and other security related information for all the FL members listed in the registration request.Docket No. SMM920250161-GR-NP

[0072] In step 873, the ML repository 841 sends (e.g., transmits, output) the generated information in the FL member registration (or registration update) response message (e.g., registration response) to the candidate FL member 816.Docket No. SMM920250161-GR-NP>>>Docket No. SMM920250161-GR-NP>>> >Table 1 information elements in a FL member registration request

[0073] In the case of registration update, similar information flow may be used. Table 2 describes the information elements in the FL member registration update request.Docket No. SMM920250161-GR-NP>>>>>Docket No. SMM920250161-GR-NP>>> >>>>Table 2 Information element FL member registration update request

[0074] Figure 9 illustrates an example of a process flow 900 in accordance with aspects of the present disclosure. The process flow 900 may implement or be implemented by aspects of the wireless communication system 100. For example, the process flow 900 may include a VAL server 916, AIMLE Server 936 and a ML repository 941, which may be one or more examples of devices described herein with reference to Figure 1.

[0075] The process flow 900 may be referred to as a procedure, including one or more operations performed by one or more of the VAL server 916, the AIMLE Server 936 and the ML repository 941.

[0076] In the following description of the process flow 900, the operations or signalling performed between one or more of the VAL server 916, the AIMLE Server 936 (e.g., thirdDocket No. SMM920250161-GR-NPnetwork entity) and the ML repository 941 (e.g., second network entity) may be performed or signalled (e.g., transmitted, received) in a different order than the example order shown, or the operations or signalling performed by one or more of the VAL server 916, the AIMLE Server 936 and the ML repository 941 may be performed or signalled (e.g., transmitted, received) in different orders or at different times. Some operations or signalling may also be omitted from the process flow 900. Additionally, although some operations or signalling may be shown to occur at different times, these operations or signalling may occur at the same time or in overlapping time periods. Process flow 900 may relate to VAL server 916 triggered VFL member discovery. Process flow 900 may relate to a case where an FL server or collaborator (e.g. VAL server 916) discovers available and capable VFL clients / participants for an ML task.

[0077] Process flow 900 starts at step 971 in which the VFL server 916 being the VAL server sends (e.g., transmits, outputs) a VFL member discovery request to the AIMLE server 936 to request the AIMLE server 936 to discover the VFL participants being the AIMLE or VAL servers or EAS in a target service area (e.g., topological or application service area or geographical area).

[0078] The discovery request (e.g., VFL member discovery request) includes at least one of the sample pool and sample binding criteria, the VFL type and compatibility aspects, the supported feature IDs, whether VAL servers and / or AIMLE servers can be considered as candidates, the supported sample IDs, the VFL task roles (e.g., coordinator, active or passive participants), a Feature Priority Level indicator, Minimum expiration Time indicator, Edge Data Network (EDN) / Data Network (DN) information, serving or allowed Public Land Mobile Network (PLMNs), service area for VFL activation, or vendor compatibility information. If a VFL task is known, the identifier of the VFL task may be assigned to AIMLE server 936 by the VAL server 916.

[0079] In step 972, the AIMLE server 936 authorizes the request.

[0080] In step 973, the AIMLE server 936 fetches (e.g., requests, by sending a request for VFL participants for participating in the VFL operation according to a discovery criterion) from the ML repository 941 the list of candidates VFL participants with the requested criteria (e.g., one or more of the discovery criterion). Such criteria (e.g., Docket No. SMM920250161-GR-NPdiscovery criterion) may include at least one of: a sample pool (e.g., aligned sample IDs); a sample binding criteria; a sample ID list; a feature set(s); a supported VFL task (or more generally AIMLE service) IDs; a VFL supported type; a VFL supported role; a service area and time of validity; a consumer type and permissions / restrictions on discovering certain FL member; a vendor compatibility; restrictions / limitations / permissions due to service agreements / Service Level Agreement (SLA)s between Mobile Network Operator (MNO) and vertical / ASP; data related event IDs and / or data set requirements

[0081] In step 974, the AIMLE server 936 sends (e.g., transmits, outputs) the discovered candidate VFL members with information on their role and capabilities. This may include VAL policies on the selection of VFL members.

[0082] Figure 10 illustrates an example of a UE 1000 in accordance with aspects of the present disclosure. The UE 1000 may include a processor 1002, a memory 1004, a controller 1006, and a transceiver 1008. The processor 1002, the memory 1004, the controller 1006, or the transceiver 1008, or various combinations thereof or various components thereof may be examples of means for performing various aspects of the present disclosure as described herein. These components may be coupled (e.g., operatively, communicatively, functionally, electronically, electrically) via one or more interfaces.

[0083] The processor 1002, the memory 1004, the controller 1006, or the transceiver 1008, or various combinations or components thereof may be implemented in hardware (e.g., circuitry). The hardware may include a processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), or other programmable logic device, or any combination thereof configured as or otherwise supporting a means for performing the functions described in the present disclosure.

[0084] The processor 1002 may include an intelligent hardware device (e.g., a general-purpose processor, a DSP, a CPU, an ASIC, an FPGA, or any combination thereof). In some implementations, the processor 1002 may be configured to operate the memory 1004. In some other implementations, the memory 1004 may be integrated into the processor 1002. The processor 1002 may be configured to execute computer-readable instructionsDocket No. SMM920250161-GR-NPstored in the memory 1004 to cause the UE 1000 to perform various functions of the present disclosure.

[0085] The memory 1004 may include volatile or non-volatile memory. The memory 1004 may store computer-readable, computer-executable code including instructions when executed by the processor 1002 cause the UE 1000 to perform various functions described herein. The code may be stored in a non-transitory computer-readable medium such the memory 1004 or another type of memory. Computer-readable media includes both non-transitory computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A non-transitory storage medium may be any available medium that may be accessed by a general-purpose or special-purpose computer.

[0086] In some implementations, the processor 1002 and the memory 1004 coupled with the processor 1002 may be configured to cause the UE 1000 to perform one or more of the functions described herein (e.g., executing, by the processor 1002, instructions stored in the memory 1004). For example, the processor 1002 may support wireless communication at the UE 1000 in accordance with examples as disclosed herein. The UE 1000 may be configured to support the arrangements described herein.

[0087] The controller 1006 may manage input and output signals for the UE 1000. The controller 1006 may also manage peripherals not integrated into the UE 1000. In some implementations, the controller 1006 may utilize an operating system such as iOS®, ANDROID®, WINDOWS®, or other operating systems. In some implementations, the controller 1006 may be implemented as part of the processor 1002.

[0088] In some implementations, the UE 1000 may include at least one transceiver 1008. In some other implementations, the UE 1000 may have more than one transceiver 1008. The transceiver 1008 may represent a wireless transceiver. The transceiver 1008 may include one or more receiver chains 1010, one or more transmitter chains 1012, or a combination thereof.

[0089] A receiver chain 1010 may be configured to receive signals (e.g., control information, data, packets) over a wireless medium. For example, the receiver chain 1010Docket No. SMM920250161-GR-NPmay include one or more antennas for receive the signal over the air or wireless medium. The receiver chain 1010 may include at least one amplifier (e.g., a low-noise amplifier (LN A)) configured to amplify the received signal. The receiver chain 1010 may include at least one demodulator configured to demodulate the receive signal and obtain the transmitted data by reversing the modulation technique applied during transmission of the signal. The receiver chain 1010 may include at least one decoder for decoding the processing the demodulated signal to receive the transmitted data.

[0090] A transmitter chain 1012 may be configured to generate and transmit signals (e.g., control information, data, packets). The transmitter chain 1012 may include at least one modulator for modulating data onto a carrier signal, preparing the signal for transmission over a wireless medium. The at least one modulator may be configured to support one or more techniques such as amplitude modulation (AM), frequency modulation (FM), or digital modulation schemes like phase-shift keying (PSK) or quadrature amplitude modulation (QAM). The transmitter chain 1012 may also include at least one power amplifier configured to amplify the modulated signal to an appropriate power level suitable for transmission over the wireless medium. The transmitter chain 1012 may also include one or more antennas for transmitting the amplified signal into the air or wireless medium.

[0091] Figure 11 illustrates an example of a processor 1100 in accordance with aspects of the present disclosure. The processor 1100 may be an example of a processor configured to perform various operations in accordance with examples as described herein. The processor 1100 may include a controller 1102 configured to perform various operations in accordance with examples as described herein. The processor 1100 may optionally include at least one memory 1104, which may be, for example, an L1 / L2 / L3 cache. Additionally, or alternatively, the processor 1100 may optionally include one or more arithmetic-logic units (ALUs) 1106. One or more of these components may be in electronic communication or otherwise coupled (e.g., operatively, communicatively, functionally, electronically, electrically) via one or more interfaces (e.g., buses).

[0092] The processor 1100 may be a processor chipset and include a protocol stack (e.g., a software stack) executed by the processor chipset to perform various operations (e.g., receiving, obtaining, retrieving, transmitting, outputting, forwarding, storing,Docket No. SMM920250161-GR-NPdetermining, identifying, accessing, writing, reading) in accordance with examples as described herein. The processor chipset may include one or more cores, one or more caches (e.g., memory local to or included in the processor chipset (e.g., the processor 1100) or other memory (e.g., random access memory (RAM), read-only memory (ROM), dynamic RAM (DRAM), synchronous dynamic RAM (SDRAM), static RAM (SRAM), ferroelectric RAM (FeRAM), magnetic RAM (MRAM), resistive RAM (RRAM), flash memory, phase change memory (PCM), and others).

[0093] The controller 1102 may be configured to manage and coordinate various operations (e.g., signalling, receiving, obtaining, retrieving, transmitting, outputting, forwarding, storing, determining, identifying, accessing, writing, reading) of the processor 1100 to cause the processor 1100 to support various operations in accordance with examples as described herein. For example, the controller 1102 may operate as a control unit of the processor 1100, generating control signals that manage the operation of various components of the processor 1100. These control signals include enabling or disabling functional units, selecting data paths, initiating memory access, and coordinating timing of operations.

[0094] The controller 1102 may be configured to fetch (e.g., obtain, retrieve, receive) instructions from the memory 1104 and determine subsequent instruction(s) to be executed to cause the processor 1100 to support various operations in accordance with examples as described herein. The controller 1102 may be configured to track memory address of instructions associated with the memory 1104. The controller 1102 may be configured to decode instructions to determine the operation to be performed and the operands involved. For example, the controller 1102 may be configured to interpret the instruction and determine control signals to be output to other components of the processor 1100 to cause the processor 1100 to support various operations in accordance with examples as described herein. Additionally, or alternatively, the controller 1102 may be configured to manage flow of data within the processor 1100. The controller 1102 may be configured to control transfer of data between registers, arithmetic logic units (ALUs), and other functional units of the processor 1100.Docket No. SMM920250161-GR-NP

[0095] The memory 1104 may include one or more caches (e.g., memory local to or included in the processor 1100 or other memory, such RAM, ROM, DRAM, SDRAM, SRAM, MRAM, flash memory, etc. In some implementations, the memory 1104 may reside within or on a processor chipset (e.g., local to the processor 1100). In some other implementations, the memory 1104 may reside external to the processor chipset (e.g., remote to the processor 1100).

[0096] The memory 1104 may store computer-readable, computer-executable code including instructions that, when executed by the processor 1100, cause the processor 1100 to perform various functions described herein. The code may be stored in a non-transitory computer-readable medium such as system memory or another type of memory. The controller 1102 and / or the processor 1100 may be configured to execute computer-readable instructions stored in the memory 1104 to cause the processor 1100 to perform various functions. For example, the processor 1100 and / or the controller 1102 may be coupled with or to the memory 1104, the processor 1100, the controller 1102, and the memory 1104 may be configured to perform various functions described herein. In some examples, the processor 1100 may include multiple processors and the memory 1104 may include multiple memories. One or more of the multiple processors may be coupled with one or more of the multiple memories, which may, individually or collectively, be configured to perform various functions herein.

[0097] The one or more ALUs 1106 may be configured to support various operations in accordance with examples as described herein. In some implementations, the one or more ALUs 1106 may reside within or on a processor chipset (e.g., the processor 1100). In some other implementations, the one or more ALUs 1106 may reside external to the processor chipset (e.g., the processor 1100). One or more ALUs 1106 may perform one or more computations such as addition, subtraction, multiplication, and division on data. For example, one or more ALUs 1106 may receive input operands and an operation code, which determines an operation to be executed. One or more ALUs 1106 be configured with a variety of logical and arithmetic circuits, including adders, subtractors, shifters, and logic gates, to process and manipulate the data according to the operation. Additionally, or alternatively, the one or more ALUs 1106 may support logical operations such as AND,Docket No. SMM920250161-GR-NPOR, exclusive-OR (XOR), not-OR (NOR), and not- AND (NAND), enabling the one or more ALUs 1106 to handle conditional operations, comparisons, and bitwise operations.

[0098] The processor 1100 may support wireless communication in accordance with examples as disclosed herein. The processor 1100 may be configured to support a means for receiving, from a second network entity, a registration request to register the second network entity for participating in a VFL operation, wherein the registration request comprises an indication of a VFL capability of the second network entity; and transmitting, to the second network entity, a registration response. Alternatively, the processor 1100 may be configured to or operable to support a means for transmitting, to a first network entity, a registration request to register the second network entity for participating in a VFL operation, wherein the registration request comprises an indication of a VFL capability of the second network entity; and receiving, from the second network entity, a registration response.

[0099] Figure 12 illustrates an example of a NE 1200 in accordance with aspects of the present disclosure. The NE 1200 may include a processor 1202, a memory 1204, a controller 1206, and a transceiver 1208. The processor 1202, the memory 1204, the controller 1206, or the transceiver 1208, or various combinations thereof or various components thereof may be examples of means for performing various aspects of the present disclosure as described herein. These components may be coupled (e.g., operatively, communicatively, functionally, electronically, electrically) via one or more interfaces.

[0100] The processor 1202, the memory 1204, the controller 1206, or the transceiver 1208, or various combinations or components thereof may be implemented in hardware (e.g., circuitry). The hardware may include a processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), or other programmable logic device, or any combination thereof configured as or otherwise supporting a means for performing the functions described in the present disclosure.

[0101] The processor 1202 may include an intelligent hardware device (e.g., a general-purpose processor, a DSP, a CPU, an ASIC, an FPGA, or any combination thereof). In some implementations, the processor 1202 may be configured to operate the memory 1204. Docket No. SMM920250161-GR-NPIn some other implementations, the memory 1204 may be integrated into the processor 1202. The processor 1202 may be configured to execute computer-readable instructions stored in the memory 1204 to cause the NE 1200 to perform various functions of the present disclosure.

[0102] The memory 1204 may include volatile or non-volatile memory. The memory 1204 may store computer-readable, computer-executable code including instructions when executed by the processor 1202 cause the NE 1200 to perform various functions described herein. The code may be stored in a non-transitory computer-readable medium such the memory 1204 or another type of memory. Computer-readable media includes both non-transitory computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A non-transitory storage medium may be any available medium that may be accessed by a general-purpose or special-purpose computer.

[0103] In some implementations, the processor 1202 and the memory 1204 coupled with the processor 1202 may be configured to cause the NE 1200 to perform one or more of the functions described herein (e.g., executing, by the processor 1202, instructions stored in the memory 1204). For example, the processor 1202 may support wireless communication at the NE 1200 in accordance with examples as disclosed herein. The NE 1200 may be configured to support a means for receiving, from a second network entity, a registration request to register the second network entity for participating in a VFL operation, wherein the registration request comprises an indication of a VFL capability of the second network entity; and transmitting, to the second network entity, a registration response.Alternatively, the NE 1200 may be configured to or operable to support a means for transmitting, to a first network entity, a registration request to register the second network entity for participating in a VFL operation, wherein the registration request comprises an indication of a VFL capability of the second network entity; and receiving, from the second network entity, a registration response.

[0104] The controller 1206 may manage input and output signals for the NE 1200. The controller 1206 may also manage peripherals not integrated into the NE 1200. In some implementations, the controller 1206 may utilize an operating system such as iOS®,Docket No. SMM920250161-GR-NPANDROID®, WINDOWS®, or other operating systems. In some implementations, the controller 1206 may be implemented as part of the processor 1202.

[0105] In some implementations, the NE 1200 may include at least one transceiver 1208. In some other implementations, the NE 1200 may have more than one transceiver 1208. The transceiver 1208 may represent a wireless transceiver. The transceiver 1208 may include one or more receiver chains 1210, one or more transmitter chains 1212, or a combination thereof.

[0106] A receiver chain 1210 may be configured to receive signals (e.g., control information, data, packets) over a wireless medium. For example, the receiver chain 1210 may include one or more antennas for receive the signal over the air or wireless medium. The receiver chain 1210 may include at least one amplifier (e.g., a low-noise amplifier (LN A)) configured to amplify the received signal. The receiver chain 1210 may include at least one demodulator configured to demodulate the receive signal and obtain the transmitted data by reversing the modulation technique applied during transmission of the signal. The receiver chain 1210 may include at least one decoder for decoding the processing the demodulated signal to receive the transmitted data.

[0107] A transmitter chain 1212 may be configured to generate and transmit signals (e.g., control information, data, packets). The transmitter chain 1212 may include at least one modulator for modulating data onto a carrier signal, preparing the signal for transmission over a wireless medium. The at least one modulator may be configured to support one or more techniques such as amplitude modulation (AM), frequency modulation (FM), or digital modulation schemes like phase-shift keying (PSK) or quadrature amplitude modulation (QAM). The transmitter chain 1212 may also include at least one power amplifier configured to amplify the modulated signal to an appropriate power level suitable for transmission over the wireless medium. The transmitter chain 1212 may also include one or more antennas for transmitting the amplified signal into the air or wireless medium.

[0108] Figure 13 illustrates a flowchart of a method 1300 in accordance with aspects of the present disclosure. The operations of the method 1300 may be implemented by a NE as described herein. In some implementations, the NE may execute a set of instructions to control the function elements of the NE to perform the described functions.Docket No. SMM920250161-GR-NP

[0109] At 1302, the method 1300 may include receiving, from a second network entity, a registration request to register the second network entity for participating in a VFL operation, wherein the registration request comprises an indication of a VFL capability of the second network entity. The operations of 1302 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 1302 may be performed by a NE as described with reference to Figure 12.

[0110] At 1304, the method 1300 may include transmitting, to the second network entity, a registration response. The operations of 1304 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 1304 may be performed by a NE as described with reference to Figure 12.[OHl] It should be noted that the method 1300 described herein describes a possible implementation, and that the operations and the steps may be rearranged or otherwise modified and that other implementations are possible.

[0112] Figure 14 illustrates a flowchart of a method 1400 in accordance with aspects of the present disclosure. The operations of the method 1400 may be implemented by a NE as described herein. In some implementations, the NE may execute a set of instructions to control the function elements of the NE to perform the described functions.

[0113] At 1402, the method 1400 may include transmitting, to a first network entity, a registration request to register the second network entity for participating in a VFL operation, wherein the registration request comprises an indication of a VFL capability of the second network entity. The operations of 1402 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 1402 may be performed by a NE as described with reference to Figure 12.

[0114] At 1404, the method 1400 may include receiving, from the second network entity, a registration response. The operations of 1404 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 1404 may be performed by a NE as described with reference to Figure 12.Docket No. SMM920250161-GR-NP

[0115] It should be noted that the method 1400 described herein describes a possible implementation, and that the operations and the steps may be rearranged or otherwise modified and that other implementations are possible.

[0116] There is provided herein a first network entity for wireless communication, comprising: at least one memory; and at least one processor coupled with the at least one memory and configured to cause the first network entity to: receive, from a second network entity, a registration request to register the second network entity for participating in a vertical federated learning, VFL, operation, wherein the registration request comprises an indication of a VFL capability of the second network entity; and transmit, to the second network entity, a registration response. Such a first network entity tends to improve VFL involving VFL participants of different capabilities.

[0117] The first network entity may be in a wireless communication network (e.g., a wireless communication system). The second network entity may be in the wireless communication network. The wireless communication network may comprise a 5G network. The wireless communication network may comprise a 6G network. The first network entity may comprise a ML repository. The first network entity may support the integration of ML in the wireless communication network. The second network entity may comprise a candidate FL member. The second network entity may participate in FL. The second network entity may participate in VFL. The second network entity may comprise a server-side entity. The second network entity may comprise a VFL client. The second network entity may comprise a VFL participant. The second network entity may comprise a VAL server. The second network entity may comprise an AIMLE server. The second network entity may comprise an application entity. The second network entity may comprise an external application server. The external application server may be external to the core network. The external application server may be external to the MNO. The AIMLE server may be external to the core network. The ML repository may be external to the core network. The AIMLE server may at an edge side. The ML repository may be at an edge side. The edge side may be a cloud side.

[0118] The registration request may comprise an FL member registration request. The registration request may comprise a FL member registration update request. TheDocket No. SMM920250161-GR-NPregistration request may comprise an FL member registration (update) request. The registration response may comprise a FL member registration response. The registration response may comprise a FL member registration update response. The registration response may comprise an FL member registration (update) response.

[0119] The VFL operation may comprise a VFL process. The VFL capability of the second network entity may comprise information related to a capability of the second network entity to support the VFL operation. The VFL operation may comprise an application-layer VFL operation. The VFL operation may be in the application layer.

[0120] The indication of the VFL capability of the second network entity may comprise an indication of at least one of: a sample pool; a sample binding criteria; a sample identifier list; a data set requirement; a data event identifier list; a feature set; a supported VFL task identifier; a VFL supported type; or a VFL supported role. The supported VFL task identifier may comprise a supported AIMLE service identifier.

[0121] The registration request may comprise a registration update request. The registration update request may comprise an FL member registration update request. The registration update request may comprise an FL member registration (update) request.

[0122] The registration update request may relate to at least one of: a change of server load of the second network entity; a change of energy status of the second network entity; a change to the VFL capability of the second network entity; unavailability of the second network entity; detection on performance degradation of the VFL operation; migration of the second network entity to a different data network; migration of the second network entity to a different edge data network; an unavailability of a data source at the second network entity; or a quality issue of a data source at the second network entity.

[0123] The at least one processor may be further configured to cause the first network entity to authorize the registration request. The at least one processor may be further configured to cause the first network entity to register the second network entity to a machine learning repository. The registration response may comprise an indication of a role of the second network entity for the VFL operation. The registration response may comprise information related to the VFL operation. The at least one processor may beDocket No. SMM920250161-GR-NPfurther configured to cause the first network entity to transmit, to a third network entity, a notification indicating the registration of the second network entity for participating in the VFL operation.

[0124] The third network entity may comprise an AIMLE server. The third network entity may comprise a VAL server. The third network entity may be part of the wireless communication network. The third network entity may participate in FL.

[0125] The at least one processor may be further configured to cause the first network entity to: receive, from the third network entity, a request for VFL participants for participating in the VFL operation according to a discovery criterion. The discovery criterion may comprise at least one of: a sample pool; a sample binding criteria; a sample identifier list; a data set requirement; a data event identifier list; a feature set; a supported VFL task identifier; a VFL supported type; a VFL supported role; a service area and a time of validity; a consumer type and permission on discovering a member; a vendor compatibility; a restriction due to a service agreement; data related event identifier; or a data set requirement. The sample pool may comprise an aligned sample identifier. The member may be a FL member. The member may be a VFL member.

[0126] There is further provided herein a method performed or performable by a first network entity, the method comprising: receiving, from a second network entity, a registration request to register the second network entity for participating in a vertical federated learning, VFL, operation, wherein the registration request comprises an indication of a VFL capability of the second network entity; and transmitting, to the second network entity, a registration response. Such a method tends to improve VFL involving VFL participants of different capabilities.

[0127] The indication of the VFL capability of the second network entity may comprise an indication of at least one of: a sample pool; a sample binding criteria; a sample identifier list; a data set requirement; a data event identifier list; a feature set; a supported VFL task identifier; a VFL supported type; or a VFL supported role.

[0128] The registration request may comprise a registration update request. The registration update request may relate to (e.g., be associated with, be caused by, be a resultDocket No. SMM920250161-GR-NPof) at least one of: a change of server load of the second network entity; a change of energy status of the second network entity; a change to the VFL capability of the second network entity; unavailability of the second network entity; detection on performance degradation of the VFL operation; migration of the second network entity to a different data network; migration of the second network entity to a different edge data network; an unavailability of a data source at the second network entity; or a quality issue of a data source at the second network entity.

[0129] The method may further comprise authorizing the registration request. The method may further comprise registering the second network entity to a machine learning repository.

[0130] The registration response may comprise an indication of a role of the second network entity for the VFL operation. The registration response may comprise information related to the VFL operation. The method may further comprise transmitting, to a third network entity, a notification indicating the registration of the second network entity for participating in the VFL operation. The method may further comprise receiving, from the third network entity, a request for VFL participants for participating in the VFL operation according to a discovery criterion.

[0131] The discovery criterion may comprise at least one of a sample pool; a sample binding criteria; a sample identifier list; a data set requirement; a data event identifier list; a feature set; a supported VFL task identifier; a VFL supported type; a VFL supported role; a service area and a time of validity; a consumer type and permission on discovering a member; a vendor compatibility; a restriction due to a service agreement; data related event identifier; or a data set requirement.

[0132] There is further provided herein a method performed or performable by a second network entity, the method comprising: transmitting, to a first network entity, a registration request to register the second network entity for participating in a vertical federated learning, VFL, operation, wherein the registration request comprises an indication of a VFL capability of the second network entity; and receiving, from the second network entity, a registration response. Such a method tends to improve VFL involving VFL participants of different capabilities.Docket No. SMM920250161-GR-NP

[0133] The indication of the VFL capability of the second network entity may comprise an indication of at least one of: a sample pool; a sample binding criteria; a sample identifier list; a data set requirement; a data event identifier list; a feature set; a supported VFL task identifier; a VFL supported type; or a VFL supported role.

[0134] The registration request may comprise a registration update request. The registration update request may relate to at least one of: a change of server load of the second network entity; a change of energy status of the second network entity; a change to the VFL capability of the second network entity; unavailability of the second network entity; detection on performance degradation of the VFL operation; migration of the second network entity to a different data network; migration of the second network entity to a different edge data network; an unavailability of a data source at the second network entity; or a quality issue of a data source at the second network entity. The registration response may comprise an indication of a role of the second network entity for the VFL operation. The registration response may comprise information related to the VFL operation.

[0135] Examples described herein generally relate to how VFL participants being server-side entities (e.g., AIMLE or VAL servers) register their capabilities to be selected as VFL clients in an application layer VFL operation (e.g., supported by AIMLE).

[0136] Examples described herein generally relate to how VFL clients being server-side entities (e.g., AIMLE or VAL servers) get discovered by the VFL server in an application layer VFL operation (e.g., supported by AIMLE).

[0137] Examples described herein generally relate to a mechanism for supporting registering and discovering VFL participants of different capabilities, where these participants are AIMLE or VAL server or EAS. Previously, networks did not consider the VFL specific information at the registration and discovery. Some examples described herein relate to registration support for the FL members being server-side entity. The registration may include information such as the sample pool and binding criteria.Docket No. SMM920250161-GR-NP

[0138] Some examples described herein relate to discovery support including means of discovering different types of VFL members from the server-side, considering also as discovery criteria information such as sample pool and binding criteria.

[0139] There is further provided herein a method for supporting at least one application server for participating in a VFL operation, the method comprising: Receiving a request for supporting the registration of the at least one application server for participating to the VFL operation, the requirement comprises information related to the VFL capability of the at least one application server; Authorizing the request of the at least one application server and registering the application server to an ML repository; Sending a response to the application server indicating the role of the application server and information related to the VFL operation; Notifying at least one further entity on the registration of the application server as VFL participant.

[0140] The registration request may comprise at least some of: sample pool / criteria; sample ID list; data set requirements; data event ID list; feature set(s); Supported VFL task (or more generally AIMLE service) IDs; VFL supported types; or VFL supported role.

[0141] The method may further comprise supporting updating the registration of the application server based on one of the following causes: Change of application server load or energy status; Change of application server capability related to VFL operation;Unavailability of the application server; Detection on performance degradation of the VFL operation; Application server migration to different DNZEDN; or Unavailability or quality issues related to the data sources at the application server / DN side.

[0142] The method may further comprise: Receiving a request to discover at least one application server, the request comprising discovery criteria related to the VFL capability and / or VFL operation; Obtaining from the ML repository at least one of the application server based on the discovery criteria; and sending a discovery response indicating the at least one discovered application server.

[0143] The discovery request may comprise at least one of: a sample pool and / or sample binding criteria, the VFL type and compatibility aspects, the supported feature IDs, whether VAL servers and / or AIMLE servers can be considered as candidates, the supportedDocket No. SMM920250161-GR-NPsample IDs, the VFL task roles (coordinator, active or passive participants), a Feature Priority Level indicator, Minimum expiration Time indicator, EDN / DN information, serving or allowed PLMNs, service area for VFL activation, or vendor compatibility information.

[0144] The discovery criteria may comprise at least one of: Sample pool (e.g., aligned sample IDs); Sample binding criteria; Sample ID list; Feature set(s); Supported VFL task (or more generally AIMLE service) IDs; VFL supported types; VFL supported role;Service area and time of validity; Consumer type and permissions / restrictions on discovering certain FL member; Vendor compatibility;Restrictions / limitations / permissions due to service agreements / SLAs between MNO and vertical / ASP; or Data related event IDs and / or data set requirements.

[0145] The discovery request may be provided by an network analytics function, an application layer analytics function, a management domain entity, a VAL server, or a combination thereof.

[0146] It should be noted that the method described herein describes a possible implementation, and that the operations and the steps may be rearranged or otherwise modified and that other implementations are possible.

[0147] The description herein is provided to enable a person having ordinary skill in the art to make or use the disclosure. Various modifications to the disclosure will be apparent to a person having ordinary skill in the art, and the generic principles defined herein may be applied to other variations without departing from the scope of the disclosure. Thus, the disclosure is not limited to the examples and designs described herein but is to be accorded the broadest scope consistent with the principles and novel features disclosed herein.Docket No. SMM920250161-GR-NP

Claims

1. CLAIMSWhat is claimed is:

1. A first network entity for wireless communication, comprising:at least one memory; andat least one processor coupled with the at least one memory and configured to cause the first network entity to:receive, from a second network entity, a registration request to register the second network entity for participating in a vertical federated learning, VFL, operation, wherein the registration request comprises an indication of a VFL capability of the second network entity; andtransmit, to the second network entity, a registration response.

2. The first network entity of claim 1, wherein the indication of the VFL capability of the second network entity comprises an indication of at least one of:a sample pool;a sample binding criteria;a sample identifier list;a data set requirement;a data event identifier list;a feature set;a supported VFL task identifier;a VFL supported type; ora VFL supported role.

3. The first network entity of claim 1 or claim 2, wherein the registration request comprises a registration update request.

4. The first network entity of claim 3, wherein the registration update request relates to at least one of:a change of server load of the second network entity;Docket No. SMM920250161-GR-NPa change of energy status of the second network entity;a change to the VFL capability of the second network entity; unavailability of the second network entity;detection on performance degradation of the VFL operation;migration of the second network entity to a different data network; migration of the second network entity to a different edge data network;an unavailability of a data source at the second network entity; ora quality issue of a data source at the second network entity.

5. The first network entity of any one of claims 1 to 4, wherein the at least one processor is further configured to cause the first network entity to:authorize the registration request.

6. The first network entity of any one of claims 1 to 5, wherein the at least one processor is further configured to cause the first network entity to:register the second network entity to a machine learning repository.

7. The first network entity of any one of claims 1 to 6, wherein the registration response comprises an indication of a role of the second network entity for the VFL operation.

8. The first network entity of any one of claims 1 to 7, wherein the registration response comprises information related to the VFL operation.

9. The first network entity of any one of claims 1 to 8, wherein the at least one processor is further configured to cause the first network entity to:transmit, to a third network entity, a notification indicating the registration of the second network entity for participating in the VFL operation.

10. The first network entity of claim 9, wherein the at least one processor is further configured to cause the first network entity to:Docket No. SMM920250161-GR-NPreceive, from the third network entity, a request for VFL participants for participating in the VFL operation according to a discovery criterion.

11. The first network entity of claim 10, wherein the discovery criterion comprises at least one of:a sample pool;a sample binding criteria;a sample identifier list;a data set requirement;a data event identifier list;a feature set;a supported VFL task identifier;a VFL supported type;a VFL supported role;a service area and a time of validity;a consumer type and permission on discovering a member;a vendor compatibility;a restriction due to a service agreement;data related event identifier; ora data set requirement.

12. A method performed or performable by a first network entity, the method comprising:receiving, from a second network entity, a registration request to register the second network entity for participating in a vertical federated learning, VFL, operation, wherein the registration request comprises an indication of a VFL capability of the second network entity; andtransmitting, to the second network entity, a registration response.

13. A method performed or performable by a second network entity, the method comprising:Docket No. SMM920250161-GR-NPtransmitting, to a first network entity, a registration request to register the second network entity for participating in a vertical federated learning, VFL, operation, wherein the registration request comprises an indication of a VFL capability of the second network entity; andreceiving, from the second network entity, a registration response.

14. The method of claim 13, wherein the indication of the VFL capability of the second network entity comprises an indication of at least one ofa sample pool;a sample binding criteria;a sample identifier list;a data set requirement;a data event identifier list;a feature set;a supported VFL task identifier;a VFL supported type; ora VFL supported role.

15. The method of claim 13 or claim 14, wherein the registration request comprises a registration update request.Docket No. SMM920250161-GR-NP

Images