Cross domain vertical federated learning involving application function and network data analytics function instances

Abstract

A method for vertical federated learning, VFL, by coordinator network function, NF, includes receiving first intermediate results associated with a first machine learning, ML, model running on / at a first participant NF. The coordinator NF receives second intermediate results associated with a second ML model running on / at a second participant NF. Based on the first intermediate results from the first participant NF and the second intermediate results from the second participant NF, the coordinator NF updates a coordinator side machine learning, ML, model and / or at least one training parameter. The coordinator NF transmits updated information to the first participant NF and the second participant NF.

Description

[0001] CROSS DOMAIN VERTICAL FEDERATED LEARNING INVOLVING APPLICATION

[0002] FUNCTION AND NETWORK DATA ANALYTICS FUNCTION INSTANCES

[0003] TECHNICAL FIELD

[0004] The present disclosure relates, in general, to wireless communications and, more particularly, systems and methods for cross domain Vertical Federated Learning (VFL) involving Application Function (AF) and Network Data Analytics Function (NWDAF) instances.

[0005] BACKGROUND

[0006] Artificial Intelligence (AI)ZMachine Learning (ML) relevant topics have been studied in SA2 Release 18 (Rel-18). For example, Horizontal Federated Learning (HFL) among multiple NWDAFs within 5thGeneration Core (5GC) has been studied in SA2 Rel-18 work item eNA_Ph3. See, 3GPP TR 23.700-81 V18.0.0, Study of Enablers for Network Automation forthe 5G System (5GS); Phase 3. The normative work is specified in 3GPP TS 23.288. See, 3GPP TS 23.288 V18.4.0, Architecture enhancements for 5G System (5GS) to support network data analytics services.

[0007] 5GC supports application layer AI / ML operations has been studied in SA2 Rel-18 work item, AIMLsys. See, TR 23.700-80 (V18.0.0), Study on 5G system support for AI / ML-based services. The normative work is in 3GPP TS 23.501 and 3GPP TS 23.502. See, 3GPP TS 23.501 V18.4.0, System architecture for the 5G System (5GS), Stage 2. See also, 3GPP TS 23.502 V18.4.0, Procedures for the 5G System (5GS), Stage 2.

[0008] Recently, a new SA2 Release 19 (Rel-19) key issue for study of 5GC support for Vertical Federated Learning (VFL) has been agreed. See, 3GPP TR 23.700-84 V0.1.0, Study on Core Network Enhanced Support for Artificial Intelligence (AI)ZMachine Learning (ML).

[0009] Key Issue on 5GC Support for VFL

[0010] This key issue aims to provide solutions for enabling 5GC support for VFL involving NWDAF andZor Application Function (AF). The main difference between HFL and VFL is that VFL enables the use of heterogeneous feature space, or in other words every participant can have different features as opposed to HFL where all participants learn the same features. For example, this means that every participant can have different neural architecture. These advantages go alongside the main aspect of not exchanging any raw data. Yet some level of coordination is still required when training and inference are performed on local models. In particular, datasets used for each local model need to share the same samples while holding different features.

[0011] In Rel-18, ML model sharing between NWDAFs has been studied as a part of HFL. However, Federated Learning between NWDAF and AF has not been studied. For example, when the NWDAFs and / or AFs are in different domains, locations, regions, etc. has not been studied.

[0012] VFL can be considered as an alternative mechanism for distributed functionalities of an ML model. Note that, as scoped in Rel-19, NWDAF and / or AF may be involved for VFL.

[0013] This Key Issue aims to study architecture enhancement to support VFL, which allows the cooperative AI / ML training and inference with the following aspects:

[0014] • Identify VFL use cases and under which conditions, and for which entities these VFL use cases show that VFL is justified to train ML models.

[0015] • Whether and how to support architecture enhancement for supporting VFL for model training and / or inference. In particular:

[0016] • Whether and how the existing NF discovery and selection needs to be enhanced.

[0017] • Whether and how ML Model training and / or inference related procedures need to be enhanced to support VFL.

[0018] • Whether and how to do performance monitoring for the ML model trained via VFL.

[0019] • Whether and how to provide ML Models to the participants in the VFL training process.

[0020] • How to support sample and feature alignment among the participating network entities when performing VFL.

[0021] NOTE 1: Application layer based VFL requiring communication between AFs and / or UEs application client, is out of scope.

[0022] NOTE 2: During the study on this KI, consultation with SA WG3 is required for handling security aspects.

[0023] NOTE 3: RAN and UE aspects are out of scope.

[0024] NOTE 4: The existing procedures defined for HFL in TS 23.288 [2] will be taken into account when studying the procedure for VFL.

[0025] See, 3GPP TR 23.700-84 VO. 1.0, Study on Core Network Enhanced Support for Artificial Intelligence (AI)ZMachine Learning (ML) There currently exist certain challenge(s), however. For example, in the existing specifications, there are procedures for FL among multiple NWDAFs within 5GC given in 3GPP TS 23.288 and solutions for 5GS assistance to application layer FL operations. However, cross domain VFL with both AF and NWDAF is not considered, and the procedures for registration, discovery, selection, and maintenance of AF in a training process are missing.

[0026] SUMMARY

[0027] Certain aspects of the disclosure and their embodiments may provide solutions to these or other challenges. For example, methods and systems are provided to cross domain VFL involving AF and NWDAF in a training process.

[0028] According to certain embodiments, a method for VFL by a coordinator NF includes receiving first intermediate results associated with a first ML model running on / at a first participant NF and receiving second intermediate results associated with a second ML model running on / at a second participant NF. Based on the first intermediate results from the first participant NF and the second intermediate results from the second participant NF, the coordinator NF updates a coordinator side ML model and / or at least one training parameter. The coordinator NF transmits updated information to the first participant NF and the second participant NF.

[0029] According to certain embodiments a coordinator NF is configured to receive first intermediate results associated with a first ML model running on / at a first participant NF and second intermediate results associated with a second ML model running on / at a second participant NF. Based on the first intermediate results from the first participant NF and the second intermediate results from the second participant NF, the coordinator NF is configured to update a coordinator side ML model and / or at least one training parameter. The coordinator NF is configured to transmit updated information to the first participant NF and the second participant NF.

[0030] According to certain embodiments, a method by a first participant NF for VFL includes transmitting, to a coordinator NF, first intermediate results associated with a first ML model running on / at the first participant NF. The first participant NF receives updated information from the coordinator NF. The updated information is based on the first intermediate results associated with the first ML model running on / at the first participant NF and second intermediate results associated with a second ML model running on / at the second participant NF. According to certain embodiments, a first participant NF for VFL is configured to transmit, to a coordinator NF, first intermediate results associated with a first ML model running on / atthe first participant NF. The first participant NF is configured to receive updated information from the coordinator NF. The updated information is based on the first intermediate results associated with the first ML model running on / at the first participant NF and second intermediate results associated with a second ML model running on / at the second participant NF.

[0031] Certain embodiments may provide one or more of the following technical advantage (s). For example, certain embodiments may provide a technical advantage of providing solutions for registration, discovery, selection, and maintenance of AF in a cross domain VFL training process with both AF and NWDF.

[0032] Other advantages may be readily apparent to one having skill in the art. Certain embodiments may have none, some, or all of the recited advantages.

[0033] BRIEF DESCRIPTION OF THE DRAWINGS

[0034] For a more complete understanding of the disclosed embodiments and their features and advantages, reference is now made to the following description, taken in conjunction with the accompanying drawings, in which:

[0035] FIGURE 1 illustrates an example architecture of one NWDAF coordinating a VFL training process, according to certain embodiments;

[0036] FIGURE 2 illustrates an example architecture of one AF coordinating a FVL training process, according to certain embodiments;

[0037] FIGURES 3A and 3B illustrate an example Registration and Discovery Procedure for VFL where one NWDAF acts as coordinator / server and the AF and other NWDAF(s) act as participants / clients, according to certain embodiments;

[0038] FIGURES 4A and 4B illustrate an example Registration and Discovery Procedure for VFL where one AF acts as coordinator / server and UE(s) and one NWDAF act as participants / clients, according to certain embodiments;

[0039] FIGURES 5A and 5B an example procedure for VFL among AF and NWDAF Instances where one NWDAF acts as coordinator / server and AF and other NWDAF(s) act as participants / clients, according to certain embodiments;

[0040] FIGURE 6 illustrates an example procedure for VFL among AF and NWDAF Instances where one AF acts as coordinator / server and UE(s) and one NWDAF act as participants / clients, according to certain embodiments; FIGURE 7 illustrates an example procedure for Maintaining VFL Processes, where one NWDAF acts as coordinator / server and the AF and other NWDAF(s) act as participants / clients, according to certain embodiments;

[0041] FIGURE 8 illustrates an example procedure for Maintaining VFE Processes where one AF acts as coordinator / server and UE(s) and one NWDAF act as participants / clients, according to certain embodiments;

[0042] FIGURE 9 illustrates an example method for VFL by a coordinator NF, according to certain embodiments;

[0043] FIGURE 10 illustrates an example method by a first participant NF for VFL, according to certain embodiments;

[0044] FIGURE 11 illustrates an example communication system, according to certain embodiments;

[0045] FIGURE 12 illustrates an example UE, according to certain embodiments;

[0046] FIGURE 13 illustrates an example network node, according to certain embodiments; and FIGURE 14 illustrates a virtualization environment in which functions implemented by some embodiments may be virtualized, according to certain embodiments.

[0047] DETAILED DESCRIPTION

[0048] Some of the embodiments contemplated herein will now be described more fully with reference to the accompanying drawings. Embodiments are provided by way of example to convey the scope of the subject matter to those skilled in the art.

[0049] As used herein, ‘node’ can be a network node or a UE. Examples of network nodes are NodeB, base station (BS), multi-standard radio (MSR) radio node such as MSR BS, eNodeB (eNB), gNodeB (gNB), Master eNB (MeNB), Secondary eNB (SeNB), integrated access backhaul (IAB) node, network controller, radio network controller (RNC), base station controller (BSC), relay, donor node controlling relay, base transceiver station (BTS), Central Unit (e.g. in a gNB), Distributed Unit (e.g. in a gNB), Baseband Unit, Centralized Baseband, C-RAN, access point (AP), transmission points, transmission nodes, Remote Radio Unit (RRU), Remote Radio Head (RRH), nodes in distributed antenna system (DAS), core network node (e.g. Mobile Switching Center (MSC), Mobility Management Entity (MME), etc.), Operations & Maintenance (O&M), Operations Support System (OSS), Self-Organizing Network (SON), positioning node (e.g. E- SMLC), etc. The terms network node and radio network node are used interchangeably herein.

[0050] Another example of a node is user equipment (UE), which is a non-limiting term and refers to any type of wireless device communicating with a network node and / or with another UE in a cellular or mobile communication system. Examples of UE are target device, device to device (D2D) UE, vehicular to vehicular (V2V), machine type UE, MTC UE or UE capable of machine to machine (M2M) communication, Personal Digital Assistant (PDA), Tablet, mobile terminals, smart phone, laptop embedded equipment (LEE), laptop mounted equipment (LME), Unified Serial Bus (USB) dongles, etc.

[0051] The term radio access technology (RAT), may refer to any RAT such as, for example, Universal Terrestrial Radio Access Network (UTRA), Evolved Universal Terrestrial Radio Access Network (E-UTRA), narrow band internet of things (NB-IoT), WiFi, Bluetooth, next generation RAT, NR, 4G, 5G, etc. Any of the equipment denoted by the terms node, network node or radio network node may be capable of supporting a single or multiple RATs.

[0052] The term signal or radio signal used herein can be any physical signal or physical channel. Examples of downlink (DL) physical signals are reference signal (RS) such as Primary Synchronization Signal (PSS), Secondary Synchronization Signal (SSS), Channel State Information-Reference Signal (CSI-RS), Demodulation Reference Signal (DMRS) signals in SS / PBCH block (SSB), discovery reference signal (DRS), Cell Specific Reference Signal (CRS), Positioning Reference Signal (PRS), etc. RS may be periodic. For example, RS occasions carrying one or more RSs may occur with certain periodicity (e.g., 20 ms, 40 ms, etc.). The RS may also be aperiodic.

[0053] Each SSB carries New Radio-Primary Synchronization Signal (NR-PSS), New RadioSecondary Synchronization Signal (NR-SSS) and New Radio-Physical Broadcast Channel (NR- PBCH) in four successive symbols. One or multiple Synchronization Signal Blocks (SSBs) are transmitted in one SSB burst which is repeated with certain periodicity such as, for example, 5 ms, 10 ms, 20 ms, 40 ms, 80 ms, and 160 ms. The UE is configured with information about SSB on cells of certain carrier frequency by one or more SS / PBCH block measurement timing configuration (SMTC) configurations. The SMTC configuration comprising parameters such as SMTC periodicity, SMTC occasion length in time or duration, SMTC time offset with regard to reference time (e.g., serving cell’s SFN) etc. Therefore, SMTC occasion may also occur with certain periodicity (e.g., 5 ms, 10 ms, 20 ms, 40 ms, 80 ms, and 160 ms). Examples of uplink (UL) physical signals are reference signals such as Sounding Reference Signals (SRS), Demodulation Reference Signals (DMRS), etc. The term physical channel refers to any channel carrying higher layer information e.g. data, control etc. Examples of physical channels are Physical Broadcast Channel (PBCH), Physical Downlink Control Channel (PDCCH), Physical Downlink Shared Channel (PDSCH), Physical Uplink Shared Channel (PUSCH), Physical Uplink Control Channel (PUCCH), Physical Uplink Shared Channel (PUSCH), Short PUSCH (sPUCCH), Short PDSCH (sPDSCH), Short PUCCH (sPUCCH), Short PUSCH (sPUSCH), MTC PDCCH (MPDCCH), Narrowband PBCH (NPBCH), Narrowband PDCCH (NPDCCH), Narrowband PDSCH (NPDSCH), Narrowband PUSCH (NPUSCH), Enhanced PDCCH (E-PDCCH), etc.

[0054] The term time resource used herein may correspond to any type of physical resource or radio resource expressed in terms of length of time. Examples of time resources are symbol, time slot, subframe, radio frame, transmission time interval (TTI), interleaving time, slot, sub-slot, mini-slot, system frame number (SFN) cycle, hyper-SFN (H-SFN) cycle, etc.

[0055] In the existing specifications, there are solutions for regular ML model training process and HFL among multiple NWDAFs within 5GC and for 5GS assistance to application layer Federated Learning operation. However, cross domain VFL with both AF and NWDAF is not considered, and the procedures for registration, discovery, selection, and maintenance of AF in a training process are missing.

[0056] Certain embodiments described herein consider the study aspect listed in the newly agreed key issue for Rel-19, and the outputs of Rel-18 on Federated Learning within 5GC and in application layer. Furthermore, certain embodiments disclosed herein propose solutions for cross domain VFL with both AF and NWDAF in a training process. The problems that are addressed include

[0057] 1) Whether and how the existing NF discovery and selection needs to be enhanced.

[0058] 2) Whether and how ML Model training related procedures need to be enhanced to support VFL.

[0059] Two scenarios are considered:

[0060] 1) One NWDAF acts as coordinator / server, one AF and the other NWDAF(s) act as participant / client in the VFL training process.

[0061] 2) One AF acts as coordinator / server, UE(s) and one NWDAF act as participant / client in the VFL training process.

[0062] The procedures for registration, discovery, selection, and maintenance of AF in a training process are considered. More specifically, the following procedures are considered in the proposed techniques, solutions, and embodiments:

[0063] ■ Registration and Discovery procedure for VFL

[0064] ■ General procedure for VFL among Multiple NWDAF Instances

[0065] ■ Procedures for Maintaining VFL Processes

[0066] FIGURE 1 illustrates an example architecture 100 of one NWDAF 102 coordinating a FVL training process, according to certain embodiments. The NWDAF 102 acts as coordinator / server, while one AF 106 and other NWDAF(s) 104a-n act as participant / client in the VFL training process. The coordinator / server NWDAF 102 may interact with the participant / client AF 106 directly or via Network Exposure Function (NEF) 108. The VFL process may involve VFL within 5GC among multiple NWDAFs 104a-n. For example, as shown in FIGURE 1, the coordinator / server NWDAF 102 may interact with other NWDAF(s) 104a-n (i.e., participant / client NWDAF(s)) for the VFL training process.

[0067] FIGURE 2 illustrates an example architecture 200 of one AF 206 coordinating a FVL training process according to certain embodiments. In the depicted example, the AF 206 acts as coordinator / server, while one NWDAF 202 and UE(s) 204a-n act as participant / client in the VFL training process. The coordinator / server AF 206 may interact with the participant / client NWDAF 202 directly or via NEF 208. The VFL process may involve VFL among multiple UEs 204a-n such as is shown in FIGURE 2, and the coordinator / server AF 206 may interact with UE(s) 204a-n (i.e., participant / client UE(s)) for the VFL training process.

[0068] Registration and Discovery Procedure for VFL One NWDAF as Coordinator / Server

[0069] FIGURES 3A and 3B illustrate an example Registration and Discovery Procedure 300 for VFL where one NWDAF 308 acts as coordinator / server and the AF 302 and other NWDAF(s) act as participants / clients, according to certain embodiments. In the illustrated embodiment, the procedure 300 is broken into three sub-procedures: the Registration procedure 310 (steps 320 to 328), the Discovery procedure 312 (steps 330 to 334), and the VFL Preparation procedure 314 (steps 336 to 344).

[0070] During the registration procedure, the NWDAF 308, which contains Model Training Logical Function (MTLF), and the AF 302 register with the Network Repository Function (NRF) 306 with each’s respective NF profde (for NWDAF containing MTLF and / or Analytics Logical Function (AnLF), AF). Specifically, at step 320, the NWDAF 308 containing MTLF registers to NRF 306 with its NF profile (VFL NWDAF profile), which includes one or more of:

[0071] ■ NF Type

[0072] ■ Address information of NF

[0073] ■ Service Area

[0074] ■ FL capability type information (i.e., VFL coordinator / server or VFL participant / client)

[0075] ■ Analytics ID(s)

[0076] ■ Time interval supporting VFL

[0077] ■ Available data information per Analytics ID o Features of data samples o Information of data samples o Data sources which can access for data collection o Availability of labels

[0078] ■ ML Model Interoperability Indicator

[0079] ■ List of Application IDs it serves

[0080] ■ Information on support operations on ML model (e.g. store ML model, train a ML model, re -train a ML model, etc.)

[0081] ■ Interoperability Information such as ML Model Interoperability Information or similar

[0082] ■ For split VFL: o Information of epoch o Information of batches (number of groups the epoch is split into) At steps 322a and 322b, the AF 302 registers to NEF 304 and NEF 304 registers to NRF 306 with its NF profde (VFL AF profde), which includes one or more of:

[0083] ■ NF Type

[0084] ■ Address information of NF

[0085] ■ Service Area

[0086] ■ FL capability type information (i.e., VFL coordinator / server or VFL participant / client)

[0087] ■ Analytics ID(s)

[0088] ■ Time interval supporting VFL

[0089] ■ Available data information per Analytics ID o Features of data samples o Information of data samples o Data sources which can access for data collection o Availability of labels

[0090] ■ ML Model Interoperability Indicator (if available)

[0091] ■ Application ID it represents

[0092] ■ Information on support operations on ML model (e.g. store ML model, train a ML model, re -train a ML model, etc.)

[0093] ■ Interoperability Information such as ML Model Interoperability Information or similar

[0094] ■ For split VFL: o Information of epoch o Information of batches (number of groups the epoch is split into) At step 324, the NRF 306 stores VFL NWDAF and VFL AF profiles.

[0095] At step 326, the NRF 306 sends a Nnrf_NF Management_NFRegister Response to NWDAF 308.

[0096] At step 328, the NRF 306 sends a Nnrf_NFManagement_NFRegister Response to AF 302.

[0097] The method may then proceed to the Discovery procedure 312 where the NWDAF 308 containing MTLF determines ML model requires VFL based on operator policy (e.g., preconfigured list of ML models) and / or consumer requirement, Analytic ID, Service Area / DNAI, or data cannot be obtained directly from data producer NF and features of data samples are not available (e.g., due to privacy reasons). At step 330, the NWDAF 308 containing MTLF discovers participants / clients from NRF by invoking the Nnrf_NFDiscovery_Request service operation. In various particular embodiments, one or more of the following criteria may be used:

[0098] ■ Analytic ID of the ML model required

[0099] ■ Model fdter information

[0100] ■ FL capability Type (i.e., VFL coordinator / server or VFL participant / client)

[0101] ■ Time Period of Interest

[0102] ■ Service Area

[0103] ■ Available data information per Analytics ID o Features of data samples o Information of data samples o Data sources which can access for data collection

[0104] ■ Application ID

[0105] ■ Information on support operations on ML model (e.g. store ML model, train a ML model, re-train a ML model, etc.)

[0106] ■ Interoperability Information such as ML Model Interoperability Information or similar

[0107] ■ For split VFL: o Information of epoch o Information of batches (number of groups the epoch is split into)

[0108] At step 332, NRF 306 authorizes NF Service Discovery. At step 334, NRF 306 transmits a Nnrf_NFDiscovery_Request Response (AF instance, NWDAF Instances) to NWDAF 308.

[0109] The method may then proceed to the VFL Preparation procedure 314 where, at step 336, the coordinator / server NWDAF 308 sends VFL preparation request to the participants / clients (AF, other NWDAF(s) containing MTLF). In particular embodiments, the request message includes the ML Preparation Flag, to check if the participants / clients can meet the ML model training requirement (e.g., Analytics ID, ML Model Interoperability information, Available data requirement (e.g. features of data samples, information of data samples, data sources), Availability time requirement (time span needed for the VFL process), Supported operations on ML model, For split VFL (e.g. epoch and batches, dimension of the output of head), feature alignment, sample alignment, etc.).

[0110] In a particular embodiment, available data requirement may include one or more of:

[0111] • A list of Event IDs of the local data for training • Features alignment for the Analytics ID

[0112] • Sample alignment

[0113] • Requirement for data sources

[0114] • Time window of the data samples

[0115] In a particular embodiment, Available time requirement may include one or more of:

[0116] • Time span needed for the VFL process (one task)

[0117] • Time span needed for complete one round of training (or one iteration, or one mini task)

[0118] • Available time for supporting VFL training

[0119] In a particular embodiment, Supported operations on ML model may include one or more of:

[0120] • Information on support operations on ML model (e.g. store ML model, train a ML model, re-train a ML model, etc.)

[0121] • Interoperability Information such as ML Model Interoperability Information or similar

[0122] In a particular embodiment, For split VFL may include one or more of:

[0123] • Epoch

[0124] • Batches

[0125] • Dimension of the output of head

[0126] At step 338, the participant(s) / client(s) (AF) 302 check whether it can meet the ML model training requirement and / or can successfully download the model if the model information is provided in the request and decides whether to join the VFL process based on operator policy (e.g., pre-configured list of ML models) and / or implementation. Example criteria used by participants / clients (AF) may include one or more of:

[0127] ■ Data availability (e.g., available features of data samples, data sources can be access to for data collection, etc.)

[0128] ■ Time availability

[0129] ■ Computation and communication capability

[0130] ■ Supported operations on ML model

[0131] ■ ML Model Interoperability information

[0132] ■ Capability to organize FL / VFL among multiple UEs

[0133] ■ Features alignment for the Analytics ID

[0134] ■ Sample alignment ■ For split VFL o Information of epoch o Information of batches (number of groups the epoch is split into) o Dimension of the output

[0135] At step 340, the participant / client (AF) 302 sends a response to the coordinator / server NWDAF 308 as to whether the participant / client (AF) 302 will join the VFL procedure. In particular embodiments, the response may include, for example, the features, dimension of the output, or the reason in the response message if it cannot join the VFL process.

[0136] In a particular embodiment, steps 336 to 340 may be repeated depending on the response from the participant / client (AF).

[0137] In a particular embodiment, the interaction for VFL preparation between the coordinator / server NWDAF 308 and the participant / client AF 302 at steps 336 to 340 may be via NEF 304.

[0138] At step 342, the coordinator / server NWDAF 308 interacts with other NWDAF(s) containing MTLF for preparation request and get response.

[0139] At step 344, the coordinator / server NWDAF 308 determines the final list of the participants / clients (AF, other NWDAF(s) containing MTLF) to be involved in the VFL procedures based on the information received in steps 334 and 340.

[0140] FIGURES 4A and 4B illustrate an example Registration and Discovery Procedure 400 for VFL where one AF acts as coordinator / server and UE(s) and one NWDAF act as participants / clients, according to certain embodiments. In the illustrated embodiment, the procedure 400 is broken into three sub-procedures: the Registration procedure 410 (steps 420 to 428), the Discovery procedure 412 (steps 430 to 434), and the VFL Preparation procedure 414 (steps 436 to 440).

[0141] Steps 420 to 428 of the registration procedure are the same as the steps 320 to 328 as illustrated in FIGURES 3 A and 3B.

[0142] The method then proceeds to steps 430 to 434 of the Discovery procedure 412 where one AF 402 acts as coordinator / server of the VFL process. During the Discover procedure 412, the AF 402 determines ML model requires VFL based on operator policy (e.g., pre-configured list of ML models) or consumer requirement, or data cannot be obtained directly from data sources and features of data samples are not available (e.g., due to privacy reasons).

[0143] The AF discovers participants / clients from NRF (or via NEF) by invoking the Nnrf_NFDiscovery_Request service operation and sending, at step 430, a Nnrf_NFDiscovery_Request. At 432, the NRF 406 authorizes NF Service Discovery. In various particular embodiments, one or more of the following criteria might be used:

[0144] ■ Analytic ID of the ML model required

[0145] ■ Model fdter information

[0146] ■ FL capability Type (i.e., VFL coordinator / server or VFL participant / client)

[0147] ■ Time Period of Interest

[0148] ■ Service Area

[0149] ■ Available data information per Analytics ID o Features of data samples o Information of data samples o Data sources which can access for data collection o Availability of labels

[0150] ■ ML Model Interoperability Indicator

[0151] ■ Information on support operations on ML model (e.g. store ML model, train a ML model, re-train a ML model, etc.)

[0152] ■ Interoperability Information

[0153] ■ For split VFL: o Information of epoch o Information of batches (number of groups the epoch is split into)

[0154] At 434, the NRF 406 transmits a Nnrf_NFDiscovery_Request Response (AF instance, NWDAF instances) to the AF 402.

[0155] The method then proceeds to steps 436 to 440 of the VFL Preparation procedure 414. Specifically, at step 436, the AF 402 sends VFL preparation request to the participant / client (NWDAF 408 containing MTLF). In a particular embodiment, the request message includes the ML Preparation Flag, to check if the participants / clients can meet the ML model training requirement (e.g., Analytics ID, ML Model Interoperability information), Available data requirement (e.g. features of data samples, information of data samples, data sources), Availability time requirement (time span needed for the VFL process), Supported operations on ML model, For split VFL (e.g. epoch and batches, dimension of the output of head), feature alignment, sample alignment, etc.).

[0156] In a particular embodiment, Available data requirement may include one or more of:

[0157] ■ A list of Event IDs of the local data for training

[0158] ■ Information on features of data samples for the Analytics ID ■ Information of data samples

[0159] ■ Information for data sources

[0160] ■ Time window of the data samples

[0161] In a particular embodiment, Available time requirement may include one or more of:

[0162] ■ Time span needed for the VFL process (one task)

[0163] ■ Time span needed for complete one round of training (or one iteration, or one mini task)

[0164] ■ Available time for supporting VFL training

[0165] In a particular embodiment, Supported operations on ML model may include one or more of:

[0166] • Information on support operations on ML model (e.g. store ML model, train a ML model, re-train a ML model, etc.)

[0167] • Interoperability Information

[0168] • For split VFL o Information of epoch o Information of batches (number of groups the epoch is split into) o Dimension of the output

[0169] At step 438, the participant / client (NWDAF 408 containing MTLF) checks whether it can meet the ML model training requirement and decides whether to join the VFL process based on operator policy (e.g., pre-configured list of ML models) and / or implementation. In a particular embodiment, example criteria used by participants / clients (NWDAF containing MTLF) may include one or more of:

[0170] ■ Data availability (e.g., available features of data samples, data sources can be access to for data collection, etc.)

[0171] ■ Time availability

[0172] ■ Computation and communication capability

[0173] ■ Supported operations on ML model

[0174] ■ ML Model Interoperability information

[0175] ■ Capability to organize FL / VFL within 5GC among multiple NWDAFs

[0176] ■ Features alignment for the Analytics ID

[0177] ■ Sample alignment

[0178] ■ For split VFL o Information of epoch o Information of batches (number of groups the epoch is split into) o Dimension of the output

[0179] At step 440, the participants / clients (NWDAF(s) 408 containing MTLF) response to the AF 402 whether it will join the FL procedure and may include, for example, the features, dimension of the output or the reason in the response message if it cannot join the VFL process.

[0180] In a particular embodiment, steps 436 to 440 may be repeated depending on the response from the participant / client (NWDAF 408 containing MTLF).

[0181] In a particular embodiment, the interaction for VFL preparation between the coordinator / server NWDAF 408 and the participant / client AF 402 at steps 436 to 440 may via NEF 406.

[0182] At step 442, the AF 402 determines the participant / client (NWDAF 408 containing MTLF) to be involved in the VFL procedures based on the information received in steps 434 and 440.

[0183] FIGURES 5A and 5B illustrates an example procedure 500 for VFL among AF 502 and NWDAF Instances 508 where one NWDAF 508 acts as coordinator / server and AF and other NWDAF(s) act as participants / clients, according to certain embodiments. In the illustrated embodiment, the corresponding procedures are as follows:

[0184] • Step 510: A VFL training process is triggered by consumer (e.g., 5GC NFs, AF, or other Entities) or according to local configuration of the coordinator / server NWDAF 508.

[0185] • Step 512: The coordinator / server NWDAF 508 selects participants / clients (AF 502, other NWDAF(s) containing MTLF) as described above with regard to FIGURES 3A and 3B.

[0186] • Step 514a and 514b: The coordinator / server NWDAF508 sends ML model training request to the selected participants / clients (AF 502, other NWDAF(s) containing MTLF). The request may include one or more of:

[0187] ■ ML model metric (e.g., accuracy, etc.)

[0188] ■ Initial ML model or ML model information (e.g., ML model address, ML model parameters, etc.)

[0189] ■ Initial VFL parameters / information (e.g., information on structure of neural network for training, number of hidden layers, connections of the nodes in adjacent layers, etc.)

[0190] ■ The maximum response time

[0191] ■ The maximum number of iterations / epochs / batches for training ■ For split VFL o Information of epoch o Information of batches o Dimension of the output of head

[0192] ■ All info available in step 336 in FIGURES 3A and 3B

[0193] ■ The participants / clients (AF) response to the NWDAF containing MTLF and may include e.g., the features, dimension of the output.

[0194] • Steps 510-512 may be repeated depending on the response from the participant / client (AF) 502.

[0195] Step 516a and 516b: Each participants / client (AF 502, other NWDAF(s) containing MTLF) collects its local data and performs training operations using local data (features of the data samples), and report intermediate results to the coordinator / server NWDAF 508. In various particular embodiments, the intermediate results may include one or more of :

[0196] ■ Intermediate local ML model

[0197] ■ Intermediate local ML model information / parameters

[0198] ■ Intermediate local training information / parameters

[0199] ■ For split VFL o Information of epoch o Information of batches o Dimension of the output o Outputs (e.g., Activations)

[0200] • Step 518: The coordinator / server NWDAF 508 aggregates (or concatenate) the intermediate ML model information or training information retrieved at step 514, to update its (global) ML model or update training parameters / setting.

[0201] • Step 520a and 520b: The coordinator / server NWDAF 508 provides intermediate coordination / global information to the participants / clients (AF 502, other NWDAF(s) containing MTLF). The intermediate coordination / global information may include one or more of:

[0202] ■ Intermediate aggregated(global) / concatenated ML model

[0203] ■ Intermediate aggregated(global) / concatenated ML model information / parameters

[0204] ■ Intermediate global / concatenated training information / parameters ■ Training setting adjustment information / requirements

[0205] ■ For split VFL o Information of epoch o Information of batches o Dimension of the output o Outputs of the concatenation (e.g. gradients)

[0206] • Step 522: Each participants / client (AF 502, other NWDAF(s) containing MTLF) updates its own ML model / training setting based on intermediate coordination / global information distributed by the coordinator / server NWDAF 508 at step 520.

[0207] • The steps 516-522 should be repeated until the training termination condition (e.g., maximum number of iterations, or the result of loss function is lower than a threshold, etc.) is reached.

[0208] • Step 524: When the VFL procedure is complete, the coordinator / server NWDAF 508 requests the participants / client (AF 502, other NWDAF(s) containing MTLF) to terminate the VFL procedure. The coordinator / server NWDAF 508 may provide the trained ML model, or the analytics generated by using the trained ML model to the consumer based on requirements from the consumer.

[0209] FIGURE 6 illustrates an example procedure 600 for VFL among AF 602 and NWDAF Instances where one AF 602 acts as coordinator / server and UE(s) and one NWDAF 608 act as participants / clients, according to certain embodiments. As illustrated, the corresponding procedures are as follows:

[0210] • Step 610: A VFL training process is triggered by consumer (e.g., 5GC NFs, AF, or other Entities) or according to local configuration of the coordinator / server NWDAF 508.

[0211] • Step 612: The AF 602 selects participant / client (NWDAF 608 containing MTLF) as described above with regard to FIGURES 5A and 5B.

[0212] • Step 614: The AF 602 sends ML model training request to the selected participant / client (NWDAF(s) containing MTLF). The request may include one or more of:

[0213] ■ ML model metric (e.g., accuracy, etc.)

[0214] ■ Initial ML model or ML model information (e.g., ML model address, ML model parameters, etc.) ■ Initial VFL parameters / information (e.g., information on structure of neural network for training, number of hidden layers, connections of the nodes in adjacent layers, etc.)

[0215] ■ The maximum response time

[0216] ■ The maximum number of iterations for training

[0217] ■ For split VFL o Information of epoch o Information of batches o Dimension of the output of head

[0218] ■ All information available in step 436 in FIGURES 4A and 4B

[0219] ■ The participants / clients (NWDAF containing MTLF) response to the AF 502 and may include, for example, the features, dimension of the output.

[0220] • Steps 612-614 may be repeated depending on the response from the participant / client (AF) 602.

[0221] Step 616: The participant / client (NWDAF(s) containing MTLF) organizes or performs training operations using local data (features of the data samples), and report intermediate results to the coordinator / server NWDAF 608. In a particular embodiment, the intermediate results may include one or more of:

[0222] ■ Intermediate local ML model

[0223] ■ Intermediate local ML model information / parameters

[0224] ■ Intermediate local training information / parameters

[0225] ■ For split VFL o Information of epoch o Information of batches o Dimension of the output o Outputs (e.g., Activations)

[0226] • Step 618: The AF 602 aggregates (or concatenate) the intermediate ML model information or training information retrieved at step 616, to update its (global) ML model or update training parameters / setting.

[0227] Step 620: The AF 602 provides intermediate coordination / global information to the participant / client (NWDAF containing MTLF). In a particular embodiment, the intermediate coordination / global information may include one or more of:

[0228] ■ Intermediate aggregated(global) / concatenated global ML model ■ Intermediate aggregated(global) / concatenated ML model information / parameters

[0229] ■ Intermediate global / concatenated training information / parameters

[0230] ■ Training setting adjustment information / requirements

[0231] ■ For split VFL o Information of epoch o Information of batches o Dimension of the output o Outputs of the concatenation (e.g. gradients)

[0232] • Step 622: The participant / client (NWDAF(s) containing MTLF) updates its own ML model / training setting based on intermediate coordination / global information distributed by the coordinator / server NWDAF at step 620.

[0233] • The steps 616-622 should be repeated until the training termination condition (e.g., maximum number of iterations, or the result of loss function is lower than a threshold, etc.) is reached.

[0234] • Step 624: When the VFL procedure is complete, the AF 602 requests the participant / client (NWDAF containing MTLF) to terminate the VFL procedure. The AF 602 may provide the trained ML model, or the analytics generated by using the trained ML model to the consumer based on requirements from the consumer.

[0235] FIGURE 7 illustrates an example procedure 700 for Maintaining VFL Processes, where one NWDAF 708 acts as coordinator / server and the AF 702 and other NWDAF(s) act as participants / clients, according to certain embodiments. In the illustrated embodiment, the corresponding procedures are as follows:

[0236] • Step 710: The coordinator / server NWDAF 708 collects the status information of the participants / clients (AF 702, other NWDAF(s) containing MTLF).

[0237] Step 712: The coordinator / server NWDAF 708 may get the updated status of current participants / clients (AF 702, other NWDAF(s) containing MTLF) via NRF 706 by using Nnrf_NFManagement service in VFL execution phase. In a particular embodiment, the updated status may include one or more of:

[0238] ■ Change of service Area

[0239] ■ Change of FL capability type information (i.e., VFL coordinator / server or VFL participant / client)

[0240] ■ Change of time interval supporting VFL ■ Change of available data information

[0241] ■ Change of features of data samples

[0242] ■ Change of the information of data samples

[0243] ■ Change of data sources which can access for data collection

[0244] ■ Change of ML Model Interoperability Indicator

[0245] ■ Change of support operations on ML model

[0246] ■ Change of ML Model Interoperability information

[0247] ■ Not support VFL anymore

[0248] ■ Change of features alignment for the Analytics ID

[0249] ■ Change of sample alignment

[0250] ■ For split VFL

[0251] ■ Change of the information of epoch

[0252] ■ Change of the information of batches

[0253] ■ Change of the dimension of the output of head

[0254] • Step714: The current participant / client (AF 702, other NWDAF(s) containing MTLF) may inform the coordinator / server NWDAF 708 that it is leaving the VFL process with Termination Request and cause code (reason for leaving, e.g., high NF load, time availability changes, capability changes, supported operations on ML model changes, etc.).

[0255] • Step 716: The coordinator / server NWDAF 708 may subscribe for analytics of the participant / client (AF 702, other NWDAF(s) containing MTLF).

[0256] • Step 718: The participant / client (AF 702, other NWDAF(s) containing MTLF) may send status report of VFL training to the coordinator / server NWDAF 708.

[0257] • Step 720: The coordinator / server NWDAF 708 checks participant / client (AF 702, other NWDAF(s) containing MTLF) status based on the received information from step 710, may determine whether reselection of participant / client and / or adjustment (e.g., adjust task assign) is needed for the next round(s) (or iteration(s)) of VFL. Steps 710-720 occur during VFL process.

[0258] • Step 722: [If re-selection or adjustment is needed as judged in step 720] The coordinator / server NWDAF 708 reselects participant / client (AF 702, other NWDAF(s) containing MTLF) and / or adjusts the task assign among the participants / clients (AF 702, other NWDAF(s) containing MTLF), etc. • Step 724: The coordinator / server NWDAF 708 sends termination request or adjustment request to the participant / client.

[0259] • Together with the termination request, optionally indicating the reason, e.g., participant / client is unselected by the coordinator / server NWDAF 708 for the VFL process, or the VFL process is suspended, etc.

[0260] • Together with the adjustment request, details adjustment requirement is given, e.g.,

[0261] ■ Change features of data samples to be used for the training

[0262] ■ Change samples for the training

[0263] ■ Change data sources for the training

[0264] ■ Adjust the requirement on response time

[0265] ■ Adjust the parameters for ML model training

[0266] ■ For split VFL

[0267] ■ Change of the batches

[0268] ■ Change of the dimension of the output of head

[0269] FIGURE 8 illustrates an example procedure 800 for Maintaining VFL Processes where one AF 802 acts as coordinator / server and UE(s) and one NWDAF 808 act as participants / clients, according to certain embodiments. In the illustrated embodiment, the corresponding procedures are as follows:

[0270] • Step 810: The AF 802 collects the status information of the participant / client (NWDAF(s) containing MTLF).

[0271] Step 812: The AF 802 may get the updated status of current participant / client (NWDAF(s) containing MTLF) via NRF 804 by using Nnrf_NFManagement service in VFL execution phase. In a particular embodiment, the updated status may include one or more of:

[0272] ■ Change of service Area

[0273] ■ Change of FL capability type information (i.e., VFL coordinator / server or VFL participant / client)

[0274] ■ Change of time interval supporting VFL

[0275] ■ Change of available data information o Change of features of data samples o Change of the information of data samples o Change of data sources which can access for data collection ■ Change of ML Model Interoperability Indicator

[0276] ■ Change of support operations on ML model

[0277] ■ Change of ML Model Interoperability information

[0278] ■ Not support VFL anymore

[0279] ■ For split VFL o Change of the information of epoch o Change of the information of batches o Change of the dimension of the output of head

[0280] • Step 814: The current participant / client (NWDAF 808 containing MTLF) may inform the AF 802 (or via NEF) that it is leaving the VFL process with Termination Request and cause code (reason for leaving, e.g., high NF load, time availability changes, capability changes, supported operations on ML model changes, etc.).

[0281] • Step 816: The participant / client (NWDAF 808 containing MTLF) may send status report of VFL training to the AF 802.

[0282] • Step 818: The AF 802 checks participant / client (NWDAF 808 containing MTLF) status based on the received information from step 810, may determine whether reselection of participant / client and / or adjustment (e.g., adjust task assign) is needed for the next round(s) (or iterations) of VFL.

[0283] • Step 820: [If re-selection or adjustment is needed as judged in step 818] The AF 802 reselects participant / client (NWDAF 808 containing MTLF) and / or adjusts the task assign among the participant / client (NWDAF 808 containing MTLF), etc.

[0284] • Step 822: The AF 802 sends termination request or adjustment request to the participant / client.

[0285] • Optionally, and together with the termination request, the AF 802 may indicate the reason for the termination such as, for example, participant / client is unselected by the AF 802 for the VFL process, or the VFL process is suspended, etc.

[0286] • Optionally, and together with the adjustment request, the AF 802 may provide a details adjustment requirement such as, for example, one or more of:

[0287] ■ Change features of data samples to be used for the training

[0288] ■ Change samples for the training

[0289] ■ Change data sources for the training

[0290] ■ Adjust the requirement on response time ■ Adjust the parameters for ML model training

[0291] ■ For split VFL

[0292] ■ Change of the batches

[0293] ■ Change of the dimension of the output of head

[0294] FIGURE 9 illustrates an example 900 method for VFL by a coordinator NF, according to certain embodiments. In the illustrated embodiment, the method begins at step at 902 when the coordinator NF receives first intermediate results associated with a first machine learning, ML, model running on / at a first participant NF. At step 904, the coordinator NF receives second intermediate results associated with a second ML model running on / at a second participant NF. Based on the first intermediate results from the first participant NF and the second intermediate results from the second participant NF, the coordinator NF updates a coordinator-side ML model and / or at least one training parameter, at step 906. At step 908, the coordinator NF transmits updated information to the first participant NF and the second participant NF.

[0295] In a particular embodiment, the coordinator NF comprises a server NF, and the first and second participant NFs comprise first and second client NFs.

[0296] In a particular embodiment, the coordinator NF aggregates and / or concatenates the first intermediate results and the second intermediate results. The coordinator-side ML model and / or the at least one training parameter is updated based on the aggregated and / or concatenated first intermediate results and the second intermediate results.

[0297] In a particular embodiment, the updated information transmitted to the first participant NF and the second participant NF comprises at least one of: third intermediate results, information of epoch, at least one output of the first intermediate results and the second intermediate results, and at least one updated training parameter.

[0298] In a particular embodiment, at least one of the first intermediate results and / or the intermediate results comprises at least one of: information of epoch and at least one model output.

[0299] In a particular embodiment, the coordinator NF transmits, to the first participant NF a first request for the first intermediate results and transmits, to the second participant NF, a second request for the second intermediate results. The first request and / or the second request comprise at least one of: at least one model metric, an initial model, at least one initial VFL parameter, and information of epoch.

[0300] In a particular embodiment, steps 902 to 908 are repeated until a termination condition is fulfilled, and the termination condition includes a maximum number of iterations being performed and / or a loss function threshold being exceeded. In a particular embodiment, the coordinator NF performs at least one of: selecting the first participant NF and the second participant NF for VFL; transmitting a participant discovery request to a Network Repository Function, NRF; and receiving information from the NRF indicating the first participant NF and the second participant NF.

[0301] In a particular embodiment, the participant discovery request includes at least one coordinator side ML model requirement, and the at least one coordinator side ML model requirement includes analytic identifier of the coordinator side ML model.

[0302] In a particular embodiment, the coordinator NF transmits, to the first and / or second NF participant, a request comprising at least one model training requirement, and the at least one model training requirement includes at least one of: analytics identifier, ML model interoperability information, Available time requirement, Feature alignment, and Sample alignment.

[0303] In a particular embodiment, the coordinator NF receives from, at least one of the first and / or second NF participant, a response indicating whether or not the at least one of the first and / or second NF participant can meet the at least one training requirement.

[0304] The coordinator NF obtains status information associated with at least one of the first participant NF and the second participant NF, and the status information includes at least one of: a change of sample alignment, and a request from at least one of the first participant NF and the second participant NF to leave the VFL process.

[0305] In a particular embodiment, the coordinator NF transmits, to the first participant NF and / or the second participant NF and / or another participant NF, at least one of: a termination request, and / or an adjustment request comprising at least one of: at least one change in features of data samples to be used for the training, a change in samples for the training, a change in data sources for the training, an adjusted requirement on response time, an adjusted parameter for ML model training, a change of the batches, and a change of the dimension of the output of head.

[0306] In further particular embodiments, the method includes any of the features of the Group A Example Embodiments.

[0307] FIGURE 10 illustrates an example method 1000 by a first participant NF for VFL, according to certain embodiments. In the illustrated embodiment, the method begins at step 1002 when the first participant NF transmits, to a coordinator NF, first intermediate results associated with a first ML model running on / at the first participant NF. At step 1004, the first participant NF receives updated information from the coordinator NF. The updated information is based on the first intermediate results associated with the first ML model running on / at the first participant NF and second intermediate results associated with a second ML model running on / at the second participant NF.

[0308] In a particular embodiment, the coordinator NF comprises a server NF, and the first participant NF comprises a first client NF.

[0309] In a particular embodiment, the updated information received from the coordinator NF comprises at least one of: third intermediate results, information of epoch, at least one output of the first intermediate results and the second intermediate results, and at least one updated training parameter.

[0310] In a particular embodiment, at least one of the first intermediate results and / or the second intermediate results includes at least one of: information of epoch, and at least one model output.

[0311] In a particular embodiment, the first participant NF receives, from the coordinator NF, a first request for the first intermediate results, and the first intermediate results is transmitted to the coordinator NF based on the first request. The first request includes at least one of: at least one model metric, an initial model, at least one initial VFL parameter, and information of epoch.

[0312] In a particular embodiment, steps 1002 and 1004 are repeated until a termination condition is fulfilled, and the termination condition includes a maximum number of iterations being performed and / or a loss function threshold being exceeded.

[0313] In a particular embodiment, the first participant NF receives, from the coordinator NF, a request to participate in the VFL, and the request to participate in the VFL includes at least one model training requirement sent from the server side to the client side. The at least one model training requirement includes at least one of: analytics identifier, ML model interoperability information, Available time requirement, Feature alignment, and Sample alignment.

[0314] In a particular embodiment, the first participant NF transmits, to the coordinator NF, a response indicating whether or not the at least one of the first and / or second NF participant can meet the at least one training requirement.

[0315] In a particular embodiment, the first participant NF transmits status information associated with the first participant NF to the coordinator NF, and the status information includes at least one of: a change of sample alignment, and a request to leave the VFL process.

[0316] In a particular embodiment, the first participant NF receives, from the coordinator NF, at least one of: a termination request, and / or an adjustment request including least one of: at least one change in features of data samples to be used for the training, a change in samples for the training, a change in data sources for the training, an adjusted requirement on response time, an adjusted parameter for ML model training, a change of the batches, and a change of the dimension of the output of head.

[0317] In further particular embodiments, the method includes any of the features of the Group B Example Embodiments.

[0318] FIGURE 11 shows an example of a communication system 1100 in accordance with some embodiments. In the example, the communication system 1100 includes a telecommunication network 1102 that includes an access network 1104, such as a radio access network (RAN), and a core network 1106, which includes one or more core network nodes 1108. The access network 1104 includes one or more access network nodes, such as network nodes 1110a and 1110b (one or more of which may be generally referred to as network nodes 1110), or any other similar 3rdGeneration Partnership Project (3GPP) access node or non-3GPP access point. The network nodes 1110 facilitate direct or indirect connection of user equipment (UE), such as by connecting UEs 1112a, 1112b, 1112c, and 1112d (one or more of which may be generally referred to as UEs 1112) to the core network 1106 over one or more wireless connections.

[0319] Example wireless communications over a wireless connection include transmitting and / or receiving wireless signals using electromagnetic waves, radio waves, infrared waves, and / or other types of signals suitable for conveying information without the use of wires, cables, or other material conductors. Moreover, in different embodiments, the communication system 1100 may include any number of wired or wireless networks, network nodes, UEs, and / or any other components or systems that may facilitate or participate in the communication of data and / or signals whether via wired or wireless connections. The communication system 1100 may include and / or interface with any type of communication, telecommunication, data, cellular, radio network, and / or other similar type of system.

[0320] The UEs 1112 may be any of a wide variety of communication devices, including wireless devices arranged, configured, and / or operable to communicate wirelessly with the network nodes 1110 and other communication devices. Similarly, the network nodes 1110 are arranged, capable, configured, and / or operable to communicate directly or indirectly with the UEs 1112 and / or with other network nodes or equipment in the telecommunication network 1102 to enable and / or provide network access, such as wireless network access, and / or to perform other functions, such as administration in the telecommunication network 1102.

[0321] In the depicted example, the core network 1106 connects the network nodes 1110 to one or more hosts, such as host 1116. These connections may be direct or indirect via one or more intermediary networks or devices. In other examples, network nodes may be directly coupled to hosts. The core network 1106 includes one more core network nodes (e.g., core network node 1108) that are structured with hardware and software components. Features of these components may be substantially similar to those described with respect to the UEs, network nodes, and / or hosts, such that the descriptions thereof are generally applicable to the corresponding components of the core network node 1108. Example core network nodes include functions of one or more of a Mobile Switching Center (MSC), Mobility Management Entity (MME), Home Subscriber Server (HSS), Access and Mobility Management Function (AMF), Session Management Function (SMF), Authentication Server Function (AUSF), Subscription Identifier De-concealing function (SIDF), Unified Data Management (UDM), Security Edge Protection Proxy (SEPP), Network Exposure Function (NEF), and / or a User Plane Function (UPF).

[0322] The host 1116 may be under the ownership or control of a service provider other than an operator or provider of the access network 1104 and / or the telecommunication network 1102 and may be operated by the service provider or on behalf of the service provider. The host 1116 may host a variety of applications to provide one or more service. Examples of such applications include live and pre-recorded audio / video content, data collection services such as retrieving and compiling data on various ambient conditions detected by a plurality of UEs, analytics functionality, social media, functions for controlling or otherwise interacting with remote devices, functions for an alarm and surveillance center, or any other such function performed by a server.

[0323] As a whole, the communication system 1100 of FIGURE 11 enables connectivity between the UEs, network nodes, and hosts. In that sense, the communication system may be configured to operate according to predefined rules or procedures, such as specific standards that include, but are not limited to: Global System for Mobile Communications (GSM); Universal Mobile Telecommunications System (UMTS); Long Term Evolution (LTE), and / or other suitable 2G, 3G, 4G, 5G standards, or any applicable future generation standard (e.g., 6G); wireless local area network (WLAN) standards, such as the Institute of Electrical and Electronics Engineers (IEEE) 802.11 standards (WiFi); and / or any other appropriate wireless communication standard, such as the Worldwide Interoperability for Microwave Access (WiMax), Bluetooth, Z-Wave, Near Field Communication (NFC) ZigBee, LiFi, and / or any low-power wide-area network (LPWAN) standards such as LoRa and Sigfox.

[0324] In some examples, the telecommunication network 1102 is a cellular network that implements 3GPP standardized features. Accordingly, the telecommunications network 1102 may support network slicing to provide different logical networks to different devices that are connected to the telecommunication network 1102. For example, the telecommunications network 1102 may provide Ultra Reliable Low Latency Communication (URLLC) services to some UEs, while providing Enhanced Mobile Broadband (eMBB) services to other UEs, and / or Massive Machine Type Communication (mMTC)ZMassive loT services to yet further UEs.

[0325] In some examples, the UEs 1112 are configured to transmit and / or receive information without direct human interaction. For instance, a UE may be designed to transmit information to the access network 1104 on a predetermined schedule, when triggered by an internal or external event, or in response to requests from the access network 1104. Additionally, a UE may be configured for operating in single- or multi-RAT or multi-standard mode. For example, a UE may operate with any one or combination of Wi-Fi, NR (New Radio) and LTE, i.e. being configured for multi -radio dual connectivity (MR-DC), such as E-UTRAN (Evolved-UMTS Terrestrial Radio Access Network) New Radio - Dual Connectivity (EN-DC).

[0326] In the example, the hub 1114 communicates with the access network 1104 to facilitate indirect communication between one or more UEs (e.g., UE 1112c and / or 1112d) and network nodes (e.g., network node 1110b). In some examples, the hub 1114 may be a controller, router, content source and analytics, or any of the other communication devices described herein regarding UEs. For example, the hub 1114 may be a broadband router enabling access to the core network 1106 for the UEs. As another example, the hub 1114 may be a controller that sends commands or instructions to one or more actuators in the UEs. Commands or instructions may be received from the UEs, network nodes 1110, or by executable code, script, process, or other instructions in the hub 1114. As another example, the hub 1114 may be a data collector that acts as temporary storage for UE data and, in some embodiments, may perform analysis or other processing of the data. As another example, the hub 1114 may be a content source. For example, for a UE that is a VR headset, display, loudspeaker or other media delivery device, the hub 1114 may retrieve VR assets, video, audio, or other media or data related to sensory information via a network node, which the hub 1114 then provides to the UE either directly, after performing local processing, and / or after adding additional local content. In still another example, the hub 1114 acts as a proxy server or orchestrator for the UEs, in particular in if one or more of the UEs are low energy loT devices.

[0327] The hub 1114 may have a constant / persi stent or intermittent connection to the network node 1110b. The hub 1114 may also allow for a different communication scheme and / or schedule between the hub 1114 and UEs (e.g., UE 1112c and / or 1112d), and between the hub 1114 and the core network 1106. In other examples, the hub 1114 is connected to the core network 1106 and / or one or more UEs via a wired connection. Moreover, the hub 1114 may be configured to connect to an M2M service provider over the access network 1104 and / or to another UE over a direct connection. In some scenarios, UEs may establish a wireless connection with the network nodes 1110 while still connected via the hub 1114 via a wired or wireless connection. In some embodiments, the hub 1114 may be a dedicated hub - that is, a hub whose primary function is to route communications to / from the UEs from / to the network node 1110b. In other embodiments, the hub 1114 may be a non-dedicated hub - that is, a device which is capable of operating to route communications between the UEs and network node 1110b, but which is additionally capable of operating as a communication start and / or end point for certain data channels.

[0328] FIGURE 12 shows a UE 1200 in accordance with some embodiments. As used herein, a UE refers to a device capable, configured, arranged and / or operable to communicate wirelessly with network nodes and / or other UEs. Examples of a UE include, but are not limited to, a smart phone, mobile phone, cell phone, voice over IP (VoIP) phone, wireless local loop phone, desktop computer, personal digital assistant (PDA), wireless cameras, gaming console or device, music storage device, playback appliance, wearable terminal device, wireless endpoint, mobile station, tablet, laptop, laptop-embedded equipment (LEE), laptop-mounted equipment (LME), smart device, wireless customer-premise equipment (CPE), vehicle-mounted or vehicle embedded / integrated wireless device, etc. Other examples include any UE identified by the 3rd Generation Partnership Project (3GPP), including a narrow band internet of things (NB-IoT) UE, a machine type communication (MTC) UE, and / or an enhanced MTC (eMTC) UE.

[0329] A UE may support device -to-device (D2D) communication, for example by implementing a 3GPP standard for sidelink communication, Dedicated Short-Range Communication (DSRC), vehicle-to-vehicle (V2V), vehicle-to-infrastructure (V2I), or vehicle-to-everything (V2X). In other examples, a UE may not necessarily have a user in the sense of a human user who owns and / or operates the relevant device. Instead, a UE may represent a device that is intended for sale to, or operation by, a human user but which may not, or which may not initially, be associated with a specific human user (e.g., a smart sprinkler controller). Alternatively, a UE may represent a device that is not intended for sale to, or operation by, an end user but which may be associated with or operated for the benefit of a user (e.g., a smart power meter).

[0330] The UE 1200 includes processing circuitry 1202 that is operatively coupled via a bus 1204 to an input / output interface 1206, a power source 1208, amemory 1212, a communication interface 1212, and / or any other component, or any combination thereof. Certain UEs may utilize all or a subset of the components shown in FIGURE 12. The level of integration between the components may vary from one UE to another UE. Further, certain UEs may contain multiple instances of a component, such as multiple processors, memories, transceivers, transmitters, receivers, etc.

[0331] The processing circuitry 1202 is configured to process instructions and data and may be configured to implement any sequential state machine operative to execute instructions stored as machine-readable computer programs in the memory 1210. The processing circuitry 1202 may be implemented as one or more hardware -implemented state machines (e.g., in discrete logic, field- programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), etc.); programmable logic together with appropriate firmware; one or more stored computer programs, general-purpose processors, such as a microprocessor or digital signal processor (DSP), together with appropriate software; or any combination of the above. For example, the processing circuitry 1202 may include multiple central processing units (CPUs).

[0332] In the example, the input / output interface 1206 may be configured to provide an interface or interfaces to an input device, output device, or one or more input and / or output devices. Examples of an output device include a speaker, a sound card, a video card, a display, a monitor, a printer, an actuator, an emitter, a smartcard, another output device, or any combination thereof. An input device may allow a user to capture information into the UE 1200. Examples of an input device include a touch-sensitive or presence-sensitive display, a camera (e.g., a digital camera, a digital video camera, a web camera, etc.), a microphone, a sensor, a mouse, a trackball, a directional pad, a trackpad, a scroll wheel, a smartcard, and the like. The presence-sensitive display may include a capacitive or resistive touch sensor to sense input from a user. A sensor may be, for instance, an accelerometer, a gyroscope, a tilt sensor, a force sensor, a magnetometer, an optical sensor, a proximity sensor, a biometric sensor, etc., or any combination thereof. An output device may use the same type of interface port as an input device. For example, a Universal Serial Bus (USB) port may be used to provide an input device and an output device.

[0333] In some embodiments, the power source 1208 is structured as a battery or battery pack. Other types of power sources, such as an external power source (e.g., an electricity outlet), photovoltaic device, or power cell, may be used. The power source 1208 may further include power circuitry for delivering power from the power source 1208 itself, and / or an external power source, to the various parts of the UE 1200 via input circuitry or an interface such as an electrical power cable. Delivering power may be, for example, for charging of the power source 1208. Power circuitry may perform any formatting, converting, or other modification to the power from the power source 1208 to make the power suitable for the respective components of the UE 1200 to which power is supplied. The memory 1210 may be or be configured to include memory such as random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), magnetic disks, optical disks, hard disks, removable cartridges, flash drives, and so forth. In one example, the memory 1210 includes one or more application programs 1214, such as an operating system, web browser application, a widget, gadget engine, or other application, and corresponding data 1216. The memory 1210 may store, for use by the UE 1200, any of a variety of various operating systems or combinations of operating systems.

[0334] The memory 1210 may be configured to include a number of physical drive units, such as redundant array of independent disks (RAID), flash memory, USB flash drive, external hard disk drive, thumb drive, pen drive, key drive, high-density digital versatile disc (HD-DVD) optical disc drive, internal hard disk drive, Blu-Ray optical disc drive, holographic digital data storage (HDDS) optical disc drive, external mini-dual in-line memory module (DIMM), synchronous dynamic random access memory (SDRAM), external micro-DIMM SDRAM, smartcard memory such as tamper resistant module in the form of a universal integrated circuit card (UICC) including one or more subscriber identity modules (SIMs), such as a USIM and / or ISIM, other memory, or any combination thereof. The UICC may for example be an embedded UICC (eUICC), integrated UICC (iUICC) or a removable UICC commonly known as ‘SIM card.’ The memory 1210 may allow the UE 1200 to access instructions, application programs and the like, stored on transitory or non-transitory memory media, to off-load data, or to upload data. An article of manufacture, such as one utilizing a communication system may be tangibly embodied as or in the memory 1210, which may be or comprise a device-readable storage medium.

[0335] The processing circuitry 1202 may be configured to communicate with an access network or other network using the communication interface 1212. The communication interface 1212 may comprise one or more communication subsystems and may include or be communicatively coupled to an antenna 1222. The communication interface 1212 may include one or more transceivers used to communicate, such as by communicating with one or more remote transceivers of another device capable of wireless communication (e.g., another UE or a network node in an access network). Each transceiver may include a transmitter 1218 and / or a receiver 1220 appropriate to provide network communications (e.g., optical, electrical, frequency allocations, and so forth). Moreover, the transmitter 1218 and receiver 1220 may be coupled to one or more antennas (e.g., antenna 1222) and may share circuit components, software or firmware, or alternatively be implemented separately. In the illustrated embodiment, communication functions of the communication interface 1212 may include cellular communication, Wi-Fi communication, LPWAN communication, data communication, voice communication, multimedia communication, short-range communications such as Bluetooth, near-field communication, location-based communication such as the use of the global positioning system (GPS) to determine a location, another like communication function, or any combination thereof. Communications may be implemented in according to one or more communication protocols and / or standards, such as IEEE 802.11, Code Division Multiplexing Access (CDMA), Wideband Code Division Multiple Access (WCDMA), GSM, LTE, New Radio (NR), UMTS, WiMax, Ethernet, transmission control protocol / intemet protocol (TCP / IP), synchronous optical networking (SONET), Asynchronous Transfer Mode (ATM), QUIC, Hypertext Transfer Protocol (HTTP), and so forth.

[0336] Regardless of the type of sensor, a UE may provide an output of data captured by its sensors, through its communication interface 1212, via a wireless connection to a network node. Data captured by sensors of a UE can be communicated through a wireless connection to a network node via another UE. The output may be periodic (e.g., once every 15 minutes if it reports the sensed temperature), random (e.g., to even out the load from reporting from several sensors), in response to a triggering event (e.g., when moisture is detected, an alert is sent), in response to a request (e.g., a user initiated request), or a continuous stream (e.g., a live video feed of a patient).

[0337] As another example, a UE comprises an actuator, a motor, or a switch, related to a communication interface configured to receive wireless input from a network node via a wireless connection. In response to the received wireless input the states of the actuator, the motor, or the switch may change. For example, the UE may comprise a motor that adjusts the control surfaces or rotors of a drone in flight according to the received input or to a robotic arm performing a medical procedure according to the received input.

[0338] A UE, when in the form of an Internet of Things (loT) device, may be a device for use in one or more application domains, these domains comprising, but not limited to, city wearable technology, extended industrial application and healthcare. Non-limiting examples of such an loT device are a device which is or which is embedded in: a connected refrigerator or freezer, a TV, a connected lighting device, an electricity meter, a robot vacuum cleaner, a voice controlled smart speaker, a home security camera, a motion detector, a thermostat, a smoke detector, a door / window sensor, a flood / moisture sensor, an electrical door lock, a connected doorbell, an air conditioning system like a heat pump, an autonomous vehicle, a surveillance system, a weather monitoring device, a vehicle parking monitoring device, an electric vehicle charging station, a smart watch, a fitness tracker, a head-mounted display for Augmented Reality (AR) or Virtual Reality (VR), a wearable for tactile augmentation or sensory enhancement, a water sprinkler, an animal- or itemtracking device, a sensor for monitoring a plant or animal, an industrial robot, an Unmanned Aerial Vehicle (UAV), and any kind of medical device, like a heart rate monitor or a remote controlled surgical robot. A UE in the form of an loT device comprises circuitry and / or software in dependence of the intended application of the loT device in addition to other components as described in relation to the UE 1200 shown in FIGURE 12.

[0339] As yet another specific example, in an loT scenario, a UE may represent a machine or other device that performs monitoring and / or measurements and transmits the results of such monitoring and / or measurements to another UE and / or a network node. The UE may in this case be an M2M device, which may in a 3GPP context be referred to as an MTC device. As one particular example, the UE may implement the 3GPP NB-IoT standard. In other scenarios, a UE may represent a vehicle, such as a car, a bus, a truck, a ship and an airplane, or other equipment that is capable of monitoring and / or reporting on its operational status or other functions associated with its operation.

[0340] In practice, any number of UEs may be used together with respect to a single use case. For example, a first UE might be or be integrated in a drone and provide the drone’s speed information (obtained through a speed sensor) to a second UE that is a remote controller operating the drone. When the user makes changes from the remote controller, the first UE may adjust the throttle on the drone (e.g. by controlling an actuator) to increase or decrease the drone’s speed. The first and / or the second UE can also include more than one of the functionalities described above. For example, a UE might comprise the sensor and the actuator, and handle communication of data for both the speed sensor and the actuators.

[0341] FIGURE 13 shows a network node 1300 in accordance with some embodiments. As used herein, network node refers to equipment capable, configured, arranged and / or operable to communicate directly or indirectly with a UE and / or with other network nodes or equipment, in a telecommunication network. Examples of network nodes include, but are not limited to, access points (APs) (e.g., radio access points), base stations (BSs) (e.g., radio base stations, Node Bs, evolved Node Bs (eNBs) and NRNodeBs (gNBs)).

[0342] Base stations may be categorized based on the amount of coverage they provide (or, stated differently, their transmit power level) and so, depending on the provided amount of coverage, may be referred to as femto base stations, pico base stations, micro base stations, or macro base stations. A base station may be a relay node or a relay donor node controlling a relay. A network node may also include one or more (or all) parts of a distributed radio base station such as centralized digital units and / or remote radio units (RRUs), sometimes referred to as Remote Radio Heads (RRHs). Such remote radio units may or may not be integrated with an antenna as an antenna integrated radio. Parts of a distributed radio base station may also be referred to as nodes in a distributed antenna system (DAS).

[0343] Other examples of network nodes include multiple transmission point (multi-TRP) 5G access nodes, multi-standard radio (MSR) equipment such as MSR BSs, network controllers such as radio network controllers (RNCs) or base station controllers (BSCs), base transceiver stations (BTSs), transmission points, transmission nodes, multi-cell / multicast coordination entities (MCEs), Operation and Maintenance (O&M) nodes, Operations Support System (OSS) nodes, Self-Organizing Network (SON) nodes, positioning nodes (e.g., Evolved Serving Mobile Location Centers (E-SMLCs)), and / or Minimization of Drive Tests (MDTs).

[0344] The network node 1300 includes a processing circuitry 1302, a memory 1304, a communication interface 1306, and a power source 1308. The network node 1300 may be composed of multiple physically separate components (e.g., a NodeB component and a RNC component, or a BTS component and a BSC component, etc.), which may each have their own respective components. In certain scenarios in which the network node 1300 comprises multiple separate components (e.g., BTS and BSC components), one or more of the separate components may be shared among several network nodes. For example, a single RNC may control multiple NodeBs. In such a scenario, each unique NodeB and RNC pair, may in some instances be considered a single separate network node. In some embodiments, the network node 1300 may be configured to support multiple radio access technologies (RATs). In such embodiments, some components may be duplicated (e.g., separate memory 1304 for different RATs) and some components may be reused (e.g., a same antenna 1310 may be shared by different RATs). The network node 1300 may also include multiple sets of the various illustrated components for different wireless technologies integrated into network node 1300, for example GSM, WCDMA, LTE, NR, WiFi, Zigbee, Z-wave, LoRaWAN, Radio Frequency Identification (RFID) or Bluetooth wireless technologies. These wireless technologies may be integrated into the same or different chip or set of chips and other components within network node 1300.

[0345] The processing circuitry 1302 may comprise a combination of one or more of a microprocessor, controller, microcontroller, central processing unit, digital signal processor, application-specific integrated circuit, field programmable gate array, or any other suitable computing device, resource, or combination of hardware, software and / or encoded logic operable to provide, either alone or in conjunction with other network node 1300 components, such as the memory 1304, to provide network node 1300 functionality.

[0346] In some embodiments, the processing circuitry 1302 includes a system on a chip (SOC). In some embodiments, the processing circuitry 1302 includes one or more of radio frequency (RF) transceiver circuitry 1312 and baseband processing circuitry 1314. In some embodiments, the radio frequency (RF) transceiver circuitry 1312 and the baseband processing circuitry 1314 may be on separate chips (or sets of chips), boards, or units, such as radio units and digital units. In alternative embodiments, part or all of RF transceiver circuitry 1312 and baseband processing circuitry 1314 may be on the same chip or set of chips, boards, or units.

[0347] The memory 1304 may comprise any form of volatile or non-volatile computer-readable memory including, without limitation, persistent storage, solid-state memory, remotely mounted memory, magnetic media, optical media, random access memory (RAM), read-only memory (ROM), mass storage media (for example, a hard disk), removable storage media (for example, a flash drive, a Compact Disk (CD) or a Digital Video Disk (DVD)), and / or any other volatile or non-volatile, non-transitory device-readable and / or computer-executable memory devices that store information, data, and / or instructions that may be used by the processing circuitry 1302. The memory 1304 may store any suitable instructions, data, or information, including a computer program, software, an application including one or more of logic, rules, code, tables, and / or other instructions capable of being executed by the processing circuitry 1302 and utilized by the network node 1300. The memory 1304 may be used to store any calculations made by the processing circuitry 1302 and / or any data received via the communication interface 1306. In some embodiments, the processing circuitry 1302 and memory 1304 is integrated.

[0348] The communication interface 1306 is used in wired or wireless communication of signaling and / or data between a network node, access network, and / or UE. As illustrated, the communication interface 1306 comprises port(s) / terminal(s) 1316 to send and receive data, for example to and from a network over a wired connection. The communication interface 1306 also includes radio front-end circuitry 1318 that may be coupled to, or in certain embodiments a part of, the antenna 1310. Radio front-end circuitry 1318 comprises filters 1320 and amplifiers 1322. The radio frontend circuitry 1318 may be connected to an antenna 1310 and processing circuitry 1302. The radio front-end circuitry may be configured to condition signals communicated between antenna 1310 and processing circuitry 1302. The radio front-end circuitry 1318 may receive digital data that is to be sent out to other network nodes or UEs via a wireless connection. The radio front-end circuitry 1318 may convert the digital data into a radio signal having the appropriate channel and bandwidth parameters using a combination of filters 1320 and / or amplifiers 1322. The radio signal may then be transmitted via the antenna 1310. Similarly, when receiving data, the antenna 1310 may collect radio signals which are then converted into digital data by the radio front-end circuitry 1318. The digital data may be passed to the processing circuitry 1302. In other embodiments, the communication interface may comprise different components and / or different combinations of components.

[0349] In certain alternative embodiments, the network node 1300 does not include separate radio front-end circuitry 1318, instead, the processing circuitry 1302 includes radio front-end circuitry and is connected to the antenna 1310. Similarly, in some embodiments, all or some of the RF transceiver circuitry 1312 is part of the communication interface 1306. In still other embodiments, the communication interface 1306 includes one or more ports or terminals 1316, the radio frontend circuitry 1318, and the RF transceiver circuitry 1312, as part of a radio unit (not shown), and the communication interface 1306 communicates with the baseband processing circuitry 1314, which is part of a digital unit (not shown).

[0350] The antenna 1310 may include one or more antennas, or antenna arrays, configured to send and / or receive wireless signals. The antenna 1310 may be coupled to the radio front-end circuitry 1318 and may be any type of antenna capable of transmitting and receiving data and / or signals wirelessly. In certain embodiments, the antenna 1310 is separate from the network node 1300 and connectable to the network node 1300 through an interface or port.

[0351] The antenna 1310, communication interface 1306, and / or the processing circuitry 1302 may be configured to perform any receiving operations and / or certain obtaining operations described herein as being performed by the network node. Any information, data and / or signals may be received from a UE, another network node and / or any other network equipment. Similarly, the antenna 1310, the communication interface 1306, and / or the processing circuitry 1302 may be configured to perform any transmitting operations described herein as being performed by the network node. Any information, data and / or signals may be transmitted to a UE, another network node and / or any other network equipment.

[0352] The power source 1308 provides power to the various components of network node 1300 in a form suitable for the respective components (e.g., at a voltage and current level needed for each respective component). The power source 1308 may further comprise, or be coupled to, power management circuitry to supply the components of the network node 1300 with power for performing the functionality described herein. For example, the network node 1300 may be connectable to an external power source (e.g., the power grid, an electricity outlet) via an input circuitry or interface such as an electrical cable, whereby the external power source supplies power to power circuitry of the power source 1308. As a further example, the power source 1308 may comprise a source of power in the form of a battery or battery pack which is connected to, or integrated in, power circuitry. The battery may provide backup power should the external power source fail.

[0353] Embodiments of the network node 1300 may include additional components beyond those shown in FIGURE 13 for providing certain aspects of the network node’s functionality, including any of the functionality described herein and / or any functionality necessary to support the subject matter described herein. For example, the network node 1300 may include user interface equipment to allow input of information into the network node 1300 and to allow output of information from the network node 1300. This may allow a user to perform diagnostic, maintenance, repair, and other administrative functions for the network node 1300.

[0354] FIGURE 14 is a block diagram illustrating a virtualization environment 1400 in which functions implemented by some embodiments may be virtualized.

[0355] In the present context, virtualizing means creating virtual versions of apparatuses or devices which may include virtualizing hardware platforms, storage devices and networking resources. As used herein, virtualization can be applied to any device described herein, or components thereof, and relates to an implementation in which at least a portion of the functionality is implemented as one or more virtual components. Some or all of the functions described herein may be implemented as virtual components executed by one or more virtual machines (VMs) implemented in one or more virtual environments 1400 hosted by one or more of hardware nodes, such as a hardware computing device that operates as a network node, UE, core network node, or host. Further, in embodiments in which the virtual node does not require radio connectivity (e.g., a core network node or host), then the node may be entirely virtualized.

[0356] Applications 1402 (which may alternatively be called software instances, virtual appliances, network functions, virtual nodes, virtual network functions, etc.) are run in the virtualization environment Q400 to implement some of the features, functions, and / or benefits of some of the embodiments disclosed herein.

[0357] Hardware 1404 includes processing circuitry, memory that stores software and / or instructions executable by hardware processing circuitry, and / or other hardware devices as described herein, such as a network interface, input / output interface, and so forth. Software may be executed by the processing circuitry to instantiate one or more virtualization layers 1406 (also referred to as hypervisors or virtual machine monitors (VMMs)), provide VMs 1408a and 1408b (one or more of which may be generally referred to as VMs 1408), and / or perform any of the functions, features and / or benefits described in relation with some embodiments described herein. The virtualization layer 1406 may present a virtual operating platform that appears like networking hardware to the VMs 1408.

[0358] The VMs 1408 comprise virtual processing, virtual memory, virtual networking or interface and virtual storage, and may be run by a corresponding virtualization layer 1406. Different embodiments of the instance of a virtual appliance 1402 may be implemented on one or more of VMs 1408, and the implementations may be made in different ways. Virtualization of the hardware is in some contexts referred to as network function virtualization (NFV). NFV may be used to consolidate many network equipment types onto industry standard high volume server hardware, physical switches, and physical storage, which can be located in data centers, and customer premise equipment.

[0359] In the context of NFV, a VM 1408 may be a software implementation of a physical machine that runs programs as if they were executing on a physical, non-virtualized machine. Each of the VMs 1408, and that part of hardware 1404 that executes that VM, be it hardware dedicated to that VM and / or hardware shared by that VM with others of the VMs, forms separate virtual network elements. Still in the context of NFV, a virtual network function is responsible for handling specific network functions that run in one or more VMs 1408 on top of the hardware 1404 and corresponds to the application 1402.

[0360] Hardware 1404 may be implemented in a standalone network node with generic or specific components. Hardware 1404 may implement some functions via virtualization. Alternatively, hardware 1404 may be part of a larger cluster of hardware (e.g. such as in a data center or CPE) where many hardware nodes work together and are managed via management and orchestration 1410, which, among others, oversees lifecycle management of applications 1402. In some embodiments, hardware 1404 is coupled to one or more radio units that each include one or more transmitters and one or more receivers that may be coupled to one or more antennas. Radio units may communicate directly with other hardware nodes via one or more appropriate network interfaces and may be used in combination with the virtual components to provide a virtual node with radio capabilities, such as a radio access node or a base station. In some embodiments, some signaling can be provided with the use of a control system 1412 which may alternatively be used for communication between hardware nodes and radio units.

[0361] Although the computing devices described herein (e.g., UEs, network nodes, hosts) may include the illustrated combination of hardware components, other embodiments may comprise computing devices with different combinations of components. It is to be understood that these computing devices may comprise any suitable combination of hardware and / or software needed to perform the tasks, features, functions and methods disclosed herein. Determining, calculating, obtaining or similar operations described herein may be performed by processing circuitry, which may process information by, for example, converting the obtained information into other information, comparing the obtained information or converted information to information stored in the network node, and / or performing one or more operations based on the obtained information or converted information, and as a result of said processing making a determination. Moreover, while components are depicted as single boxes located within a larger box, or nested within multiple boxes, in practice, computing devices may comprise multiple different physical components that make up a single illustrated component, and functionality may be partitioned between separate components. For example, a communication interface may be configured to include any of the components described herein, and / or the functionality of the components may be partitioned between the processing circuitry and the communication interface. In another example, non-computationally intensive functions of any of such components may be implemented in software or firmware and computationally intensive functions may be implemented in hardware.

[0362] In certain embodiments, some or all of the functionality described herein may be provided by processing circuitry executing instructions stored on in memory, which in certain embodiments may be a computer program product in the form of a non-transitory computer-readable storage medium. In alternative embodiments, some or all of the functionalities may be provided by the processing circuitry without executing instructions stored on a separate or discrete device-readable storage medium, such as in a hard-wired manner. In any of those particular embodiments, whether executing instructions stored on a non-transitory computer-readable storage medium or not, the processing circuitry can be configured to perform the described functionality. The benefits provided by such functionality are not limited to the processing circuitry alone or to other components of the computing device but are enjoyed by the computing device as a whole, and / or by end users and a wireless network generally.

[0363] EXAMPLE EMBODIMENTS

[0364] Group A Example Embodiments

[0365] Example Embodiment 1. A method for vertical federated learning, VFL, by a coordinator network function, NF, the method comprising: receiving first model data associated with a first machine learning, ML, model running on / at a first participant NF; receiving second model data associated with a second ML model running on / at a second participant NF; based on the first model data from the first participant NF and the second model data from the second participant NF, updating a global machine learning, ML, model and / or at least one training parameter; and transmitting updated information to the first participant NF and the second participant NF.

[0366] Example Embodiment 2. The method of Example Embodiment 1, wherein: the coordinator NF comprises a first Network Data Analytics Function, NWDAF, the first participant NF comprises a first Application Function, AF, the second participant NF comprises a second AF or a second NWDAF.

[0367] Example Embodiment 3. The method of Example Embodiment 1, wherein: the coordinator NF comprises a first AF, the first participant NF comprises a first Network Data Analytics Function, NWDAF, the second participant NF comprises a second AF or a second NWDAF.

[0368] Example Embodiment 4. The method of any one of Example Embodiments 1 to 3, wherein the coordinator NF comprises a server NF, and wherein the first and second participant NFs comprise first and second client NFs.

[0369] Example Embodiment 5. The method of any one of Example Embodiments 1 to 4, comprising: aggregating and / or concatenating the first model data and the second model data, and wherein the global ML model and / or the at least one training parameter is updated based on the aggregated and / or concatenated first model data and the second model data.

[0370] Example Embodiment 6. The method of any one of Example Embodiments 1 to 5, wherein the updated information transmitted to the first participant NF and the second participant NF comprises at least one of: coordination information, global information, an updated global ML model, intermediate aggregated(global) / concatenated ML model; intermediate aggregated(global) / concatenated ML model information / parameters; intermediate global / concatenated training information / parameters; training setting adjustment information / requirements; information of epoch; information of batches; dimension of the output; outputs of the concatenation (e.g. gradients); an updated training parameter / setting.

[0371] Example Embodiment 7. The method of any one of Example Embodiments 1 to 6, wherein at least one of the first model data and / or the second model data comprises at least one of: an intermediate local ML model; intermediate local ML model information; at least one intermediate local ML model parameter; intermedial local training information; at least one intermediate local parameter; information of epoch; information of batches; dimension of the model output; at least one model output.

[0372] Example Embodiment 8. The method of any one of Example Embodiments 1 to 7, comprising at least one of: transmitting, to the first participant NF a first request for the first model data; and transmitting, to the second participant NF, a second request for the second model data, and wherein the first request and / or the second request comprise at least one of: at least one model metric; an initial model; model information; model address; model parameters; initial VFL parameters and / or information; a maximum response time; a maximum number of iterations, epochs, and / or batches for training; information of epoch; information of batches; and dimension of the model output of head.

[0373] Example Embodiment 9. The method of any one of Example Embodiments 1 to 8, comprising repeating the steps of Example Embodiment 1 until a termination condition is fulfilled, and wherein the termination condition comprises a maximum number of iterations and / or a loss function threshold.

[0374] Example Embodiment 10. The method of any one of Example Embodiments 1 to 9, comprising at least one of: selecting the first participant NF and the second participant NF for VFL; transmitting a participant discovery request to a Network Repository Function, NRF; and receiving information from the NRF indicating the first participant NF and the second participant NF.

[0375] Example Embodiment 11. The method of Example Embodiment 10, wherein the participant discovery request comprises at least one global ML model requirement, and wherein the at least one global ML model requirement comprises at least one of: analytic identifier of the ML model required; model filter information; VFL capability; Time Period of Interest; Service Area; Available data information per Analytics identifier (e.g., features of data samples, information of data samples, and / or data sources which can access for data collection); Application identifier; information on support operations on ML model (e.g. store ML model, train a ML model, re-train a ML model, etc.); interoperability information; information of epoch; information of batches (number of groups the epoch is split into).

[0376] Example Embodiment 12. The method of any one of Example Embodiments 10 to 11, comprising transmitting, to the first and / or second NF participant, a request to participate in the VFL, and wherein the request to participate in the VFL comprises at least one model training requirement, and wherein the at least one model training requirement comprises at least one of: analytics identifier; ML model interoperability information; Available data requirement; Available time requirement; Supported operations on ML model; Epoch information; Batches information; Dimension of the output of head; Feature alignment; and Sample alignment.

[0377] Example Embodiment 13. The method of Example Embodiment 12, wherein at least one of: the available data requirements comprises at least one of: a list of Event identifiers of the local data for training; features alignment for the Analytics identifier; sample alignment; requirement for data sources; and time window of the data samples, and the available time requirements comprises at least one of: time span needed for the VFL process (one task); time span needed for complete one round of training (or one iteration, or one mini task); and available time for supporting VFL training.

[0378] Example Embodiment 14. The method of any one of Example Embodiments 10 to 13, comprising receiving from, at least one of the first and / or second NF participant, a response indicating participation in the VFL.

[0379] Example Embodiment 15. The method of any one of Example Embodiments 1 to 14, comprising transmitting, to a Network Repository Function, NRF, a registration request, and wherein the registration comprises a NF profile associated with the NF coordinator, and wherein the NF profile comprises at least one of: NF Type, Address information of NF, Service Area, FL capability type information, Analytics ID(s), Time interval supporting VFL, Available data information per Analytics identifier, Features of data samples, Information of data samples, Data sources which can access for data collection, Availability of labels, ML Model Interoperability Indicator, Application identifier, Information on support operations on ML model (e.g. store ML model, train a ML model, re-train a ML model, etc.), Interoperability Information such as ML Model Interoperability Information or similar, Information of epoch, and Information of batches.

[0380] Example Embodiment 16. The method of any one of Example Embodiments 1 to 15, comprising obtaining status information associated with at least one of the first participant NF and the second participant NF, and wherein the status information comprises at least one of: a change of service Area, a change of FL capability type information, a change of time interval supporting VFL, a change of available data information, a change of features of data samples, a change of the information of data samples, a change of data sources which can access for data collection, a change of ML Model Interoperability Indicator, a change of support operations on ML model, a change of ML Model Interoperability information, an indication to not support VFL, a change of features alignment for the Analytics identifier, a change of sample alignment, a change of the information of epoch, a change of the information of batches, and a change of the dimension of the output of head. Example Embodiment 17. The method of Example Embodiment 16, wherein obtaining the status information comprises: transmitting, to an NRF, a subscriber request; and based on the subscriber request, receiving the status information associated with at least one of the first participant NF and the second participant NF.

[0381] Example Embodiment 18. The method of any one of Example Embodiments 16 to 17, wherein the status information indicates that at least one of the first participant NF and the second participant NF are terminating the VFL process and / or a termination cause.

[0382] Example Embodiment 19. The method of any one of Example Embodiments 16 to 18, comprising transmitting a subscription request for receiving analytics of at least one of the first participant NF and the second participant NF.

[0383] Example Embodiment 20. The method of any one of Example Embodiments 16 to 19, comprising determining, based on the status information, whether reselection of participant NFs is needed and / or whether assignment and / or roles should be reassigned among participants.

[0384] Example Embodiment 21. The method of Example Embodiment 20, comprising transmitting, to the first participant NF and / or second participant NF and / or another participant NF a termination request and / or an adjustment request, and wherein the adjustment request comprises at least one of: at least one change in features of data samples to be used for the training, a change in samples for the training, a change in data sources for the training, an adjusted requirement on response time, an adjusted parameter for ML model training, a change of the batches, and a change of the dimension of the output of head.

[0385] Example Embodiment 22. A network node comprising processing circuitry configured to perform any of the methods of Example Embodiments 1 to 21.

[0386] Example Embodiment 23. A network node configured to perform any of the methods of Example Embodiments 1 to 21.

[0387] Example Emboidment 24. The network node of any one of Example Embodiments 22 to 23, wherein the network node is a core network node.

[0388] Example Embodiment 25. A computer program comprising instructions which when executed on a computer perform any of the methods of Example Embodiments 1 to 21.

[0389] Example Embodiment 26. A computer program product comprising computer program, the computer program comprising instructions which when executed on a computer perform any of the methods of Example Embodiments 1 to 21. Example Embodiment 27. A non-transitory computer readable medium storing instructions which when executed by a computer perform any of the methods of Example Embodiments 1 to 21.

[0390] Group B Example Embodiments

[0391] Example Embodiment 28. A method by a first participant network function, NF, for vertical federated learning, VFL, the method comprising: transmitting, to a coordinator NF, first model data associated with a first machine learning, ML, model running on / at the first participant NF; receiving updated information from the coordinator NF, the updated information being based on the first model data associated with the first ML model running on / at the first participant NF and second model data associated with a second ML model running on / at the second participant NF.

[0392] Example Embodiment 29. The method of Example Embodiment 28, wherein: the coordinator NF comprises a first Network Data Analytics Function, NWDAF, the first participant NF comprises a first Application Function, AF.

[0393] Example Embodiment 30. The method of Example Embodiment 28, wherein: the coordinator NF comprises a first AF, the first participant NF comprises a first Network Data Analytics Function, NWDAF, or a second AF.

[0394] Example Embodiment 31. The method of any one of Example Embodiments 28 to 30, wherein the coordinator NF comprises a server NF, and wherein the first participant NF comprises a first client NF.

[0395] Example Embodiment 32. The method of any one of Example Embodiments 28 to 31, wherein the updated information received from the coordinator NF comprises at least one of: coordination information, global information, an updated global ML model, intermediate aggregated(global) / concatenated ML model, intermediate aggregated(global) / concatenated ML model information / parameters, intermediate global / concatenated training information / parameters, training setting adjustment information / requirements, information of epoch, information of batches, dimension of the output, outputs of the concatenation (e.g. gradients), an updated training parameter / setting .

[0396] Example Embodiment 33. The method of any one of Example Embodiments 28 to 32, wherein at least one of the first model data and / or the second model data comprises at least one of: an intermediate local ML model; intermediate local ML model information; at least one intermediate local ML model parameter; intermedial local training information; at least one intermediate local parameter; information of epoch; information of batches; dimension of the model output; at least one model output.

[0397] Example Embodiment 34. The method of any one of Example Embodiments 28 to 33, comprising receiving, from the coordinator NF, a first request for the first model data, and wherein the first model data is transmitted to the coordinator NF based on the first request, and wherein the first request comprises at least one of: at least one model metric; an initial model; model information; model address; model parameters; initial VFL parameters and / or information; a maximum response time; a maximum number of iterations, epochs, and / or batches for training; information of epoch; information of batches; and dimension of the model output of head.

[0398] Example Embodiment 35. The method of any one of Example Embodiments 28 to 34, comprising repeating the steps of Example Embodiment 1 until a termination condition is fulfilled, and wherein the termination condition comprises a maximum number of iterations and / or a loss function threshold.

[0399] Example Embodiment 36. The method of any one of Example Embodiments 28 to 35, further comprising receiving, from the coordinator NF, a request to participate in the VFL, and wherein the request to participate in the VFL comprises at least one model training requirement, and wherein the at least one model training requirement comprises at least one of: analytics identifier; ML model interoperability information; Available data requirement; Available time requirement; Supported operations on ML model; Epoch information; Batches information; Dimension of the output of head; Feature alignment; and Sample alignment.

[0400] Example Embodiment 37. The method of Example Embodiment 36, wherein at least one of: the available data requirements comprises at least one of: a list of Event identifiers of the local data for training; features alignment for the Analytics identifier; sample alignment; requirement for data sources; and time window of the data samples, and the available time requirements comprises at least one of: time span needed for the VFL process (one task); time span needed for complete one round of training (or one iteration, or one mini task); and available time for supporting VFL training.

[0401] Example Embodiment 38. The method of any one of Example Embodiments 36 to 37, comprising transmitting, to the coordinator NF, a response indicating participation in the VFL.

[0402] Example Embodiment 39. The method of any one of Example Embodiments 28 to 38, comprising transmitting, to a Network Repository Function, NRF, a registration request.

[0403] Example Embodiment 40. The method of Example Embodiment 39, wherein the registration comprises a NF profile associated with the participant NF, and wherein the NF profile comprises at least one of: NF Type, Address information of NF, Service Area, FL capability type information, Analytics ID(s), Time interval supporting VFL, Available data information per Analytics identifier, Features of data samples, Information of data samples, Data sources which can access for data collection, Availability of labels, ML Model Interoperability Indicator, Application identifier, Information on support operations on ML model (e.g. store ML model, train a ML model, re-train a ML model, etc.), Interoperability Information such as ML Model Interoperability Information or similar, Information of epoch, and Information of batches.

[0404] Example Embodiment 41. The method of any one of Example Embodiments 28 to 40, comprising transmitting status information associated with the first participant NF to the coordinator NF, and wherein the status information comprises at least one of: a change of service Area, a change of FL capability type information, a change of time interval supporting VFL, a change of available data information, a change of features of data samples, a change of the information of data samples, a change of data sources which can access for data collection, a change of ML Model Interoperability Indicator, a change of support operations on ML model, a change of ML Model Interoperability information, an indication to not support VFL, a change of features alignment for the Analytics identifier, a change of sample alignment, a change of the information of epoch, a change of the information of batches, and a change of the dimension of the output of head.

[0405] Example Embodiment 42. The method of Example Embodiment 41, wherein the status information indicates that the first participant NF is terminating the VFL process and / or a termination cause.

[0406] Example Embodiment 43. The method of any one of Example Embodiments 28 to 42, comprising transmitting analytics of the first participant NF.

[0407] Example Embodiment 44. The method of any one of Example Embodiments 28 to 43, comprising receiving, from the coordinator NF, a termination request and / or an adjustment request, and wherein the adjustment request comprises at least one of: at least one change in features of data samples to be used for the training, a change in samples for the training, a change in data sources for the training, an adjusted requirement on response time, an adjusted parameter for ML model training, a change of the batches, and a change of the dimension of the output of head.

[0408] Example Embodiment 45. A network node comprising processing circuitry configured to perform any of the methods of Example Embodiments 28 to 44. Example Embodiment 46. A network node configured to perform any of the methods of Example Embodiments 28 to 44.

[0409] Example Emboidment 47. The network node of any one of Example Embodiments 28 to 44, wherein the network node is a core network node. Example Embodiment 48. A computer program comprising instructions which when executed on a computer perform any of the methods of Example Embodiments 28 to 44.

[0410] Example Embodiment 49. A computer program product comprising computer program, the computer program comprising instructions which when executed on a computer perform any of the methods of Example Embodiments 28 to 44. Example Embodiment 50. A non-transitory computer readable medium storing instructions which when executed by a computer perform any of the methods of Example Embodiments 28 to 44.

Claims

CLAIMS1. A method (1400) for vertical federated learning, VFL, by a coordinator network function (102), NF, the method comprising: receiving (1402) first intermediate results associated with a first machine learning, ML, model running on / at a first participant NF(104a); receiving (1404) second intermediate results associated with a second ML model running on / at a second participant NF (104b); based on the first intermediate results from the first participant NF and the second intermediate results from the second participant NF, updating (1406) a coordinator side machine learning, ML, model and / or at least one training parameter; and transmitting (1408) updated information to the first participant NF and the second participant NF.

2. The method of Claim 1, wherein: the coordinator NF comprises a server NF, and the first and second participant NFs comprise first and second client NFs.

3. The method of any one of Claims 1 to 2, comprising: aggregating and / or concatenating the first intermediate results and the second intermediate results, and wherein the coordinator-side ML model and / or the at least one training parameter is updated based on the aggregated and / or concatenated first intermediate results and the second intermediate results.

4. The method of any one of Claims 1 to 3, wherein the updated information transmitted to the first participant NF and the second participant NF comprises at least one of: third intermediate results, information of epoch, at least one output of the first intermediate results and the second intermediate results, and at least one updated training parameter.

5. The method of any one of Claims 1 to 4, wherein at least one of the first intermediate results and / or the intermediate results comprises at least one of: information of epoch, and at least one model output.

6. The method of any one of Claims 1 to 5, comprising at least one of:transmitting, to the first participant NF a first request for the first intermediate results; and transmitting, to the second participant NF, a second request for the second intermediate results, and wherein the first request and / or the second request comprise at least one of: at least one model metric, an initial model, at least one initial VFL parameter, and information of epoch.

7. The method of any one of Claims 1 to 6, comprising repeating the steps of Claim 1 until a termination condition is fulfilled, and wherein the termination condition comprises a maximum number of iterations being performed and / or a loss function threshold being exceeded.

8. The method of any one of Claims 1 to 7, comprising at least one of: selecting the first participant NF and the second participant NF for VFL; transmitting a participant discovery request to a Network Repository Function, NRF; and receiving information from the NRF indicating the first participant NF and the second participant NF.

9. The method of Claim 8, wherein the participant discovery request comprises at least one coordinator side ML model requirement, and wherein the at least one coordinator side ML model requirement comprises at least one analytic identifier of the coordinator side ML model.

10. The method of any one of Claims 8 to 9, comprising transmitting, to the first and / or second NF participant, a request comprising at least one model training requirement, and wherein the at least one model training requirement comprises at least one of: analytics identifier,ML model interoperability information,Available time requirement,Feature alignment, andSample alignment.

11. The method of Claim 10, comprising receiving from, at least one of the first and / or second NF participant, a response indicating whether or not the at least one of the first and / or second NF participant can meet the at least one training requirement.

12. The method of any one of Claims 1 to 11, comprising obtaining status information associated with at least one of the first participant NF and the second participant NF, and wherein the status information comprises at least one of: a change of sample alignment, and a request from at least one of the first participant NF and the second participant NF to leave the VFL process.

13. The method of any one of Claims 1 to 12, comprising transmitting, to the first participant NF and / or the second participant NF and / or another participant NF, at least one of: a termination request, and / or an adjustment request comprising at least one of: at least one change in features of data samples to be used for the training, a change in samples for the training, a change in data sources for the training, an adjusted requirement on response time, an adjusted parameter for ML model training, a change of the batches, and a change of the dimension of the output of head.

14. A method (1500) by a first participant network function, NF (104a), for vertical federated learning, VFL, the method comprising: transmitting (1502), to a coordinator NF (102), first intermediate results associated with a first machine learning, ML, model running on / at the first participant NF; and receiving (1504) updated information from the coordinator NF, the updated information being based on the first intermediate results associated with the first ML model running on / at the first participant NF and second intermediate results associated with a second ML model running on / at the second participant NF (104b).

15. The method of Claim 14, wherein the coordinator NF comprises a server NF, and wherein the first participant NF comprises a first client NF.

16. The method of any one of Claims 14 to 15, wherein the updated information received from the coordinator NF comprises at least one of: third intermediate results, information of epoch, at least one output of the first intermediate results and the second intermediate results, andat least one updated training parameter.

17. The method of any one of Claims 14 to 16, wherein at least one of the first intermediate results and / or the second intermediate results comprises at least one of: information of epoch, and at least one model output.

18. The method of any one of Claims 14 to 17, comprising receiving, from the coordinator NF, a first request for the first intermediate results, and wherein: the first intermediate results is transmitted to the coordinator NF based on the first request, and the first request comprises at least one of: at least one model metric, an initial model, at least one initial VFL parameter, and information of epoch.

19. The method of any one of Claims 14 to 18, comprising repeating the steps of Claim 1 until a termination condition is fulfilled, and wherein the termination condition comprises a maximum number of iterations being performed and / or a loss function threshold being exceeded.

20. The method of any one of Claims 14 to 19, further comprising receiving, from the coordinator NF, a request to participate in the VFL, and wherein the request to participate in the VFL comprises at least one model training requirement, and wherein the at least one model training requirement comprises at least one of: analytics identifier,ML model interoperability information,Available time requirement,Feature alignment, andSample alignment.

21. The method of Claim 20, comprising transmitting, to the coordinator NF, a response indicating whether or not the at least one of the first and / or second NF participant can meet the at least one training requirement.

22. The method of any one of Claims 14 to 21, comprising transmitting status information associated with the first participant NF to the coordinator NF, and wherein the status information comprises at least one of:a change of sample alignment, and a request to leave the VFL process.

23. The method of any one of Claims 14 to 22, comprising receiving, from the coordinator NF, at least one of: a termination request, and / or an adjustment request comprising at least one of: at least one change in features of data samples to be used for the training, a change in samples for the training, a change in data sources for the training, an adjusted requirement on response time, an adjusted parameter for ML model training, a change of the batches, and a change of the dimension of the output of head.

24. A network node operating as a coordinator network function, NF (102), for vertical federated learning, VFL, the network node configured to: receive first intermediate results associated with a first machine learning, ML, model running on / at a first participant NF; receive second intermediate results associated with a second ML model running on / at a second participant NF; based on the first intermediate results from the first participant NF and the second intermediate results from the second participant NF, update a coordinator side machine learning, ML, model and / or at least one training parameter; and transmit updated information to the first participant NF and the second participant NF.

25. The network node of Claim 24, configured to perform any of the methods of Claims 2 to 13.

26. A network node operating as a first participant network function, NF (104a), for vertical federated learning, VFL, the network node configured to: transmit, to a coordinator NF, first intermediate results associated with a first machine learning, ML, model running on / at the first participant NF; and receive updated information from the coordinator NF, the updated information being based on the first intermediate results associated with the first ML model running on / at the firstparticipant NF and second intermediate results associated with a second ML model running on / at the second participant NF.

27. The network node of Claim 26, configured to perform any of the methods of Claims 15 to23.

Images