System and apparatus for training a global model and a method in association thereto

Abstract

System (100), apparatus (102) and a method (300) for are disclosed. The method (300) includes determining a global model status; transmitting at least one signal for a local model update based on the global model status; and determining the local model update to the global model based on the at least one signal.

Description

SYSTEM AND APPARATUS FOR TRAINING A GLOBAL MODEL AND A METHOD IN ASSOCIATION THERETOField Of Invention

[0001] The present disclosure generally relates to one or both of a system and an apparatus for training a global model in association with, for example, a User Equipment (UE) usable for communication. The present disclosure further relates a method which can be associated with the system and / or the apparatus.Background of Invention

[0002] Generally, energy efficiency and power saving would be helpful in communication networks, for example, a 3rd Generation Partnership Project (3GPP) 5G (fifth generation) New Radio (NR) standard-based telecommunications network.

[0003] Current techniques may not address the issue of training a global model in a communication network. This may lead to problems such as excessive overhead signaling and unnecessary energy consumption when updating a global model, for example an Artificial Intelligence / Machine Learning (AIML) model. Thus, the current techniques may not facilitate energy efficiency and power saving in an optimal manner.

[0004] The present disclosure contemplates that it would be helpful to address or at least mitigate one or more issues in relation to conventional techniques for facilitating energy efficiency and power saving when training a global model.Summary of the Invention

[0005] According to a first aspect of the present invention, there is provided a method for training a global model, the method comprising: determining a global model status; transmitting at least one signal for a local model update based on the globalmodel status; and determining the local model update to the global model based on the at least one signal.

[0006] Advantageously, the method as described herein can reduce overhead signaling for a model training phase.

[0007] In an embodiment, the method further comprises receiving the at least one signal associated with the local model update; and analyzing the at least one signal to determine the local model update to the global model.

[0008] In an embodiment, the global model is an Artificial Intelligence / Machine Learning (AIML) Federated Learning model.

[0009] In an embodiment, the global model status comprises a model maturity condition based on a convergence threshold.

[0010] In an embodiment, the convergence threshold comprises at least one of: model performance accuracy, dataset capabilities and / or model configuration parameters associated with a User Equipment (UE).

[0011] In an embodiment, transmitting the at least one signal comprises transmitting via at least one of: User Equipment (UE) specific message, UE capability message associated with dataset capabilities of the UE and / or Medium Access Control Control Element (MAC CE).

[0012] In an embodiment, determining the local model update to the global model comprises enabling the local model update to the global model if the convergence threshold is not met; or disabling the local model update to the global model if the convergence threshold is met.

[0013] In an embodiment, the method further comprises transmitting the local model update to the global model via a measurement report associated with dataset capabilities of a User Equipment (UE).

[0014] In an embodiment, there is provided a computer program comprising instructions which, when the program is executed by a computer, cause the computer to carry out at least one of the at least one of the input step and the processing step according to the method of the first aspect.

[0015] In an embodiment, there is provided a computer readable storage medium having data stored therein representing software executable by a computer, the software including instructions, when executed by the computer, to carry out at least one of the input step and the processing step according to the method of the first aspect.

[0016] In an embodiment, there is provided an apparatus for training a global model comprising: a first module configured to receive at least one signal associated with a local model update; a second module configured to at least one of process and facilitate the method of the first aspect to generate at least one output signal; and a third module configured to communicate at least one output signal, wherein the output signal corresponds to a control signal for training the global model based on the determination of the local model update to the global model.

[0017] In an embodiment, the apparatus corresponds to a User Equipment (UE) communicable with a device corresponding to a base station, and wherein the base station corresponds to a Next generation Node B (gNB) configured to receive the at least one output signal from the UE.

[0018] In an embodiment, there is provided a system comprising: at least one apparatus(es); and at least one device(s), wherein the apparatus(es) and the device(s) are capable of being coupled via at least one of wired coupling and wireless coupling.Brief Description of the Drawings

[0019] Embodiments of the disclosure are described hereinafter with reference to the following drawings, in which:

[0020] Fig. 1A shows a schematic diagram illustrating a system for training a global model which can include at least one apparatus, according to an embodiment of the invention.

[0021] Figs. 1 B to 1 C show example scenarios in association with the system of Fig. 1A, according to an embodiment of the invention.

[0022] Fig. 2 shows a schematic diagram illustrating the apparatus of Fig. 1A in further detail, according to an embodiment of the invention.

[0023] Fig. 3 shows a method in association with the system of Fig. 1A, according to an embodiment of the invention.

[0024] Fig. 4A to Fig. 4C show schematic diagrams illustrating the flow of information in association with the method of Fig. 3, according to an embodiment of the inventionDetailed Description

[0025] The present specification discloses apparatus for performing the operations of the methods. Such apparatus may be specially constructed for the required purposes, or may comprise a computer or other device selectively activated or reconfigured by a computer program stored in the computer. The algorithms and displays presented herein are not inherently related to any particular computer or other apparatus. Various machines may be used with programs in accordance with the teachings herein. Alternatively, the construction of more specialized apparatus to perform the required method steps may be appropriate. The structure of a computer will appear from the description below.

[0026] In addition, the present specification also implicitly discloses a computer program, in that it would be apparent to the person skilled in the art that the individual steps of the method described herein may be put into effect by computer code. The computer program is not intended to be limited to any particular programming language and implementation thereof. It will be appreciated that a variety of programming languages and coding thereof may be used to implement the teachings of the disclosure contained herein. Moreover, the computer program is not intended to be limited to any particular control flow. There are many other variants of the computer program, which can use different control flows without departing from the spirit or scope of the disclosure.

[0027] Furthermore, one or more of the steps of the computer program may be performed in parallel rather than sequentially. Such a computer program may be stored on any computer readable medium. The computer readable medium may include storage devices such as magnetic or optical disks, memory chips, or other storage devices suitable for interfacing with a computer. The computer readable medium may also include a hard-wired medium such as exemplified in the Internet system, or wireless medium such as exemplified in the mobile telephone system. The computer program when loaded and executed on such a computer effectively results in an apparatus that implements the steps of the preferred method.

[0028] The present disclosure generally contemplates the facilitation and optimization of a network (for example in association with 3GPP based standard / specification etc.) and / or user equipment (UE) efficiency (for example energy efficiency or power saving), in accordance with an embodiment of the invention. Specifically, the present disclosure contemplates the possibility of training a global model in connection with 3GPP standard(s).

[0029] The present disclosure generally contemplates that Artificial Intelligence / Machine Learning (AIML) for 3GPP Release18 wireless communication may be applied to multiple cases for Physical (PHY) I Media Access Control (MAC) layers and higher layers. An example of an AIML technique is Federated Learning (FL), where AIML-based local model updates are collected from multiple users (e.g.,User Equipment or UE) to the global model on a server such that the global model (e.g., a base station or gNB) is updated in an iterative way for model training or inference.

[0030] The present disclosure contemplates that without considering the global model performance status such as model convergence, signalling for model training may be inefficient as there may be a significant number of UEs that may cause data diversity.

[0031] The present disclosure further contemplates that local model updates from multiple UEs to the global model on the server or the base station (e.g. gNB) may be selectively enabled or disabled depending on the global model status (or maturity).

[0032] In the above manner, each UE may or may not perform the local model update to the server and overhead signaling can thus be reduced to minimize signaling of inference. Power saving and energy consumption efficiency can possibly be facilitated in the network, in accordance with an embodiment of the invention.

[0033] The foregoing will be discussed in further detail with reference to Fig. 1 to Fig. 4 hereinafter.

[0034] Referring to Fig. 1A, a schematic diagram illustrating a system 100 for training a global model is shown, according to an embodiment of the invention. The system 100 can, for example, be suitable for facilitating energy and improve power efficiency, in accordance with an embodiment of the invention.

[0035] As shown, the system 100 can include one or more apparatuses 102, at least one device 104 and, optionally, a communication network 106, in accordance with an embodiment of the invention.

[0036] The apparatus(es) 102 can be coupled to the device(s) 104. Specifically, the apparatus(es) 102 can, for example, be coupled to the device(s) 104 via the communication network 106, in accordance with an embodiment of the invention.

[0037] In one embodiment, the apparatus(es) 102 can be coupled to the communication network 106 and the device(s) 104 can be coupled to the communication network 106. Coupling can be by manner of one or both of wired coupling and wireless coupling. The apparatus(es) 102 can, in general, be configured to communicate with the device(s) 104 via the communication network 106, according to an embodiment of the invention.

[0038] The apparatus(es) 102 can, for example, be associated with or correspond to or include one or more user equipment (UE) which can carry one or more computers, in accordance with an embodiment of the invention. For example, an apparatus 102 can correspond to a UE carrying at least one computer (e.g. an electronic device or module having computing capabilities such as an electronic mobile device which can be carried into a vehicle or an electronic module which can be installed in a vehicle, in accordance with an embodiment of the invention) which can be configured to perform one or more processing tasks in association with adaptive / dynamic / gradual control, in accordance with an embodiment of the invention.

[0039] In an embodiment, the apparatus(es) 102 can, for example, be configured to receive one or more input signals and perform at least one processing task based on the input signal(s) in a manner to generate one or more output signals. The input signal(s) can, for example, be communicated from the device(s) 104 and received by the apparatus(es) 102, in accordance with an embodiment of the invention. The input signal can be a signal for a local model update based on a global model status. As a possible option, the output signal(s) can, for example, be communicated from the apparatus(es) 102, in accordance with an embodiment of the invention. The output signal may correspond to a control signal for training a global model based on the determination of the local model update to the global model. The apparatus(es) 102 will be discussed later in further detail with reference to Fig. 2, according to an embodiment of the invention.

[0040] The device(s) 104 can, for example, be associated with / correspond to at least one base station, where the at least one base station can be a Next GenerationNode B (gNB). Moreover, the device(s) 104 can, for example, be configured to carry / be associated with / include one or more computers (e.g., an electronic device / module having computing capabilities) which can, for example, be configured to perform one or more processing tasks in association with the base station. The device(s) 104 can be configured to generate one or more input signals which can be communicated to the apparatus(es) 102, in accordance with an embodiment of the invention. This will be discussed later in further detail in the context of an example scenario, in accordance with an embodiment of the invention.

[0041] The communication network 106 can, for example, correspond to an Internet communication network, a cellular-based communication network, a wired-based communication network, a Global Navigation Satellite System (GNSS) based communication network, a wireless-based communication network, or any combination thereof. Communication (e.g., between the apparatuses 102 and / or between the apparatus(es) 102 and the device(s) 104) via the communication network 106 can be by manner of one or both of wired communication and wireless communication.

[0042] As mentioned, the apparatus(es) 102 can, for example, be configured to receive at least one input signal and perform at least one processing task in association with dynamic / adaptive / gradual control on the input signal(s) in a manner so as to generate at least one output signal. Moreover, the device(s) 104 can, for example, be configured to generate (and communicate) the input signal(s) to the apparatus(es) 102, in accordance with an embodiment of the invention. Accordingly, the device(s) 104 can determine the global model status and communicate or transmit at least one input signal for a local model update to the apparatus(es) 102. This will be discussed, in accordance with an embodiment of the invention, in the context of an example scenario with reference to Fig. 1 B and 1 C, hereinafter.

[0043] Fig. 1 B shows an example scenario in association with the system of Fig. 1A, according to an embodiment of the invention. Specifically, Fig. 1 B shows an example of a wireless network for Artificial Intelligence / Machine Learning (AIML) based Federated Learning (FL). As shown in the Figure, a global model (e.g. an AIMLmodel) at a base station (e.g. gNB) is in communication with multiple users (or User Equipment or UE). Each of the users (or UE) may include a local model (e.g. AIML model) having their own dataset and the global model may receive the local model updates from each of the UEs for global model training and inference. The global model may also transmit relevant dataset to each of the UE for model update data exchange.

[0044] In such communications, UEs providing local model updates may contribute to the global model performance degradation such as model divergence because of a high variety of local datasets or data diversity. Moreover, as there may be device (or UE) heterogeneity and statistical heterogeneous dataset, many communication rounds of model training may become burdensome as a result of overhead signalling. In accordance with an embodiment of the invention, overhead signalling can be reduced by considering the global model performance status such as model convergence. In doing so, signalling for the global model training can be efficient even if there are UEs that can cause data diversity.

[0045] Fig. 1 C shows an example scenario of Federated Learning (FL) in AIML global model training in a network, according to an embodiment of the present invention. In an embodiment, gNB-UE (or base station - user) signaling to support model update information exchange can be inefficient when the global model convergence status is not considered. For example and as shown in the Figure, a large number of UEs that are pre-selected for local model support in FL may send their own local model updates to the global model at the gNB (or base station) based on either periodic or event-triggering ways. The base station (or gNB or global model) may transmit a downlink message to the FL model UEs for local model update reporting and the UEs report their local model update. This may lead to an increase in overhead signaling particularly when the global model at the base station (or gNB) gets close to target maturity.

[0046] The above-described aspect(s) of the system 100 of the present invention can also apply analogously (all) the aspect(s) of a below described apparatus 102 of the present invention. Likewise, all below described aspect(s) of the apparatus 102 ofthe invention can also apply analogously (all) the aspect(s) of above-described system 100 of the invention.

[0047] The aforementioned apparatus(es) 102 or User Equipment (UE) will be discussed in further detail with reference to Fig. 2 hereinafter.

[0048] Referring to Fig. 2, a schematic diagram illustrating an apparatus 102 is shown in further detail in the context of an example implementation 200, according to an embodiment of the invention.

[0049] In the example implementation 200, the apparatus 102 can correspond to an electronic module 200a. The electronic module 200a can, in one example, correspond to a mobile device which can, for example, be carried into the vehicle by a user, in accordance with an embodiment of the invention. In another example, the electronic module 200a can correspond to an electronic device which can be installed / mounted in the vehicle, in accordance with an embodiment of the invention. In this regard, the electronic module 200a can be considered to be carried by the vehicle (e.g., either carried into the vehicle by a user or installed / mounted in the vehicle).

[0050] It is contemplated that the electronic module 200a can be capable of performing one or more processing tasks in association with adaptive / dynamic / gradual control related processing, in accordance with an embodiment of the invention.

[0051] The electronic module 200a can, for example, include a casing 200b. Moreover, the electronic module 200a can, for example, carry any one of a first module 202, a second module 204, a third module 206, or any combination thereof.

[0052] In one embodiment, the electronic module 200a can carry a first module 202, a second module 204 and / or a third module 206. In a specific example, the electronic module 200a can carry a first module 202, a second module 204 and a third module 206, in accordance with an embodiment of the invention.

[0053] In this regard, it is appreciable that, in one embodiment, the casing 200b can be shaped and dimensioned to carry any one of the first module 202, the second module 204 and the third module 206, or any combination thereof.

[0054] The first module 202 can be coupled to one or both of the second module 204 and the third module 206. The second module 204 can be coupled to one or both of the first module 202 and the third module 206. The third module 206 can be coupled to one or both of the first module 202 and the second module 204. In one example, the first module 202 can be coupled to the second module 204 and the second module 204 can be coupled to the third module 206, in accordance with an embodiment of the invention. Coupling between the first module 202, the second module 204 and / or the third module 206 can, for example, be by manner of one or both of wired coupling and wireless coupling. Each of the first module 202, the second module 204 and the third module 206 can correspond to one or both of a hardware-based module and a software-based module, according to an embodiment of the invention.

[0055] In one example, the first module 202 can correspond to a hardware-based receiver which can be configured to receive one or more input signals. The input signal(s) can, for example, be communicated from the device(s) 104 (or base station e.g., a gNB), in accordance with an embodiment of the invention.

[0056] The second module 204 can, for example, correspond to a hardware-based processor which can be configured to perform one or more processing tasks (e.g., in a manner so as to generate one or more output signals) as will be discussed later in further detail with reference to Fig. 3, in accordance with an embodiment of the invention.

[0057] The third module 206 can correspond to a hardware-based transmitter which can be configured to communicate one or more output signals from the electronic module 200a. The output signal(s) can, for example, include one or more instructions / commands / control signals in association with the aforementioned dynamic / adaptive / gradual control configuration / determination strategy so as to facilitate efficiency (e.g., power / energy efficiency and / or communication efficiency),in accordance with an embodiment of the invention. For example, the output signal(s) can be a control signal(s) to train a global model.

[0058] The present disclosure contemplates the possibility that the first and second modules 202, 204 can be an integrated software-hardware based module, for example, an electronic part which can carry a software program or algorithm in association with receiving and processing functions or an electronic module programmed to perform the functions of receiving and processing. The present disclosure further contemplates the possibility that the first and third modules 202, 206 can be an integrated software-hardware based module, for example an electronic part which can carry a software program or algorithm in association with receiving and transmitting functions or an electronic module programmed to perform the functions of receiving and transmitting. The present disclosure yet further contemplates the possibility that the first and third modules 202, 206 can be an integrated hardware module, for example a hardware-based transceiver, capable of performing the functions of receiving and transmitting.

[0059] The apparatus 102 (or UE) can, for example, be further configured to process the input signal(s), as will be discussed later in further detail with reference to Fig. 3, in a manner so as to generate one or more output signals in a manner so as to facilitate efficiency, for example power efficiency or energy efficiency, in accordance with an embodiment of the invention. In one specific example, the output signal(s) can include one or more control signals to facilitate some form of dynamic / adaptive / gradual control configuration / determination strategy so as to facilitate efficiency, for example power efficiency or energy efficiency, in accordance with an embodiment of the invention. For example, the output signal(s) can be a control signal(s) to train a global model.

[0060] The above-described aspect(s) of the apparatus 102 of the present invention can also apply analogously (all) the aspect(s) of a below described processing / communication method of the present invention. Likewise, all below described aspect(s) of the method of the invention can also apply analogously (all) the aspect(s) of above described apparatus 102 of the invention. It is to beappreciated that these remarks apply analogously to the earlier discussed system 100 of the present disclosure.

[0061] Referring to Fig. 3, a method 300 (or a communication method) for training a global model, for example an Artificial Intelligence / Machine Learning (AIML) Federated Learning (FL) model, in association with the system 100 is shown, according to an embodiment of the invention.

[0062] The method 300 can, for example, be suitable for facilitating energy efficiency, network optimization and power saving in accordance with an embodiment of the invention.

[0063] The method 300 can include any one of an input step 302, a processing step 304 and an output step 306, or any combination thereof, in accordance with an embodiment of the invention.

[0064] In an embodiment, the processing method 300 can include the input step 302. In another embodiment, the processing method 300 can include the input step 302 and the processing step 304. In another embodiment, the processing method 300 can include the input step 302, the processing step 304 and the output step 306. In yet another embodiment, the processing method 300 can include the processing step 304 and one or both of the input step 302 and the output step 306. In yet a further embodiment, the processing method 300 can include the input step 302, the processing step 304 and the output step 306. In yet a further additional embodiment, the processing method 300 can include the processing step 304. In yet another further additional embodiment, the processing method 300 can include any one of or any combination of the input step 302, the processing step 304 and the output step 306 (i.e. , the input step 302, the processing step 304 and / or the output step 306).

[0065] With regard to the input step 302, one or more input signal(s) can be received. For example, the input signal(s) can be communicated from the device(s) 104 and can be received by an apparatus 102, in accordance with an embodiment of the invention.

[0066] The input step 302 can include receiving at least one input signal associated with a local model update, which can be based on a determination of a global model status. The global model can be an Artificial Intelligence / Machine Learning (AIML) Federated Learning model and the global model status may include a model maturity condition based on a convergence threshold. The convergence threshold can include at least one of: model performance accuracy, dataset capabilities and / or model configuration parameters associated with a User Equipment (UE).

[0067] With regard to the processing step 304, at least a processing task can be performed in association with the received input signal(s) in a manner so as to generate one or more output signals, in accordance with an embodiment of the invention.

[0068] The processing step 304 may include at least one of: determining the local model update to the global model based on the at least one signal; receiving the at least one signal associated with the local model update; and analyzing the at least one signal to determine the local model update to the global model. The processing step 304 may further include enabling the local model update to the global model if the convergence threshold is not met; or disabling the local model update to the global model if the convergence threshold is met. The processing step 304 can also include transmitting the local model update to the global model via a measurement report associated with dataset capabilities of the User Equipment (UE).

[0069] In an embodiment, with a given pool of available UEs involved in Federated Learning which can provide local model updates to the gNB (or base station or global model), local model update reports from each individual UE to the gNB can be enabled or disabled. Specifically, if a global model maturity condition is met for a configured threshold, the gNB (or base station) may disable local model update reports from selected UEs.

[0070] In an example embodiment, the processing step 304 may be performed by the device 104 (base station or gNB) and may further include determining the globalmodel status and transmitting at least one signal (or input signals) for a local model update based on the global model status to the apparatus 102 (UE). Transmission of the at least one signal (or input signals) includes transmitting via at least one of: User Equipment (UE) specific message, UE capability message associated with dataset capabilities of the UE and / or Medium Access Control Control Element (MAC CE).

[0071] In an embodiment, the threshold for global model maturity condition can be configured based on the UE model performance accuracy or dataset capabilities or Model configuration parameters of the UE, thereby determining which UE is selected for providing the local model update. The UE may indicate its dataset capabilities in the UE Capability message and the UE may report the data set capabilities in the measurement report for a dynamic update of the dataset capabilities, in accordance with an embodiment of the invention.

[0072] In an alternate embodiment, if the global model maturity condition is not met and requires intensive model training for convergence, the gNB (or base station) may enable local model update reports from many or all available UEs. The configurable criteria to determine enable or disable for local model update reporting may be set by network.

[0073] In an example embodiment, transmitting of the input signal to the UE can be via UE Specific message or Medium Access Control Control Element (MAC CE) by using 1 bit to enable or disable local model update reports of the UE. For example, if the gNB (or base station) signals “1” in the UE Specific message, then local model update report is disabled for the UE. Alternatively, if the gNB (or base station) signals “0” in the UE Specific message, then local model update report is enabled for the UE.

[0074] With regards to the output step 306, the output signal(s) can, for example, be communicated, as an option, in accordance with an embodiment of the invention. For example, the output signal(s) can optionally be communicated from the apparatus 102. In a more specific example, the output signal(s) can optionally be communicated from the apparatus 102 to one or both of at least one device 104, in accordance with an embodiment of the invention. In an embodiment, the apparatus102 (or UE) may also perform the input step 302, the processing step 304 and the output step 306.

[0075] The present disclosure further contemplates a computer program (not shown) which can include instructions which, when the program is executed by a computer (not shown), cause the computer to carry out the input step 302, the processing step 304 and / or the output step 306 as discussed with reference to the method 300. For example, the computer program can include instructions which, when the program is executed by a computer, cause the computer to carry out the input step 302 and / or the processing step 304, in accordance with an embodiment of the invention.

[0076] The present disclosure yet further contemplates a computer readable storage medium (not shown) having data stored therein representing software executable by a computer (not shown), the software including instructions, when executed by the computer, to carry out the input step 302, the processing step 304 and / or the output step 306 as discussed with reference to the method 300. For example, the computer readable storage medium can have data stored therein representing software executable by a computer, the software including instructions, when executed by the computer, cause the computer to carry out the input step 302 and / or the processing step 304, in accordance with an embodiment of the invention.

[0077] Further in view of the foregoing, it is appreciable that the present disclosure generally contemplates an apparatus 102 for training the global model which can include a first module 202, a second module 204 and / or a third module 206.

[0078] The first module 202 can be configured to receive one or more input signals. The input signal(s) can, for example, be associated with a local model update based on a global model status.

[0079] The second module 204 can be configured to process and / or facilitate processing of the input signal(s) according to the method 300 as discussed earlier to generate one or more output signals.

[0080] The third module 206 can be configured to communicate one or more output signals. The output signal(s) can, for example, correspond to one or more control signals for training the global model based on the determination of the local model update to the global model.

[0081] In one embodiment, the apparatus 102 can correspond to a User Equipment (UE) which can communicate with a device 104 corresponding to a base station. The base station can, for example, correspond to a Next generation Node B (gNB) which can be configured to communicate one or more signals (e.g., input signal(s)) to the UE.

[0082] Yet further in view of the foregoing, it is appreciable that the present disclosure generally contemplates a system 100 which can include one or more apparatuses 102 and one or more devices 104. The apparatus(es) 102 and the device(s) 104 can, for example, be capable of being coupled via wired coupling and / or wireless coupling.

[0083] It should be appreciated that the embodiments described above can be combined in any manner as appropriate (e.g., one or more embodiments as discussed in the “Detailed Description” section can be combined with one or more embodiments as described in the “Summary of the Invention” section).

[0084] It should be further appreciated by the person skilled in the art that variations and combinations of embodiments described above, not being alternatives or substitutes, may be combined to form yet further embodiments.

[0085] In one example, the possibility of the output signal(s) being communicated from the apparatus(es) 102 was discussed. It is appreciable that the output signal(s) need not necessarily be communicated from the apparatus(es) 102. Specifically, the possibility that the output signal(s) need not necessarily be communicated outside of the apparatus(es) 102 is contemplated, in accordance with an embodiment of the invention. More specifically, the output signal(s) can, for example, correspond to internal command(s) / instruction(s) (e.g., communicated only within an apparatus 102) for adaptively controlling operational configuration of an apparatus 102, in accordance with an embodiment of the invention.

[0086] In another example, application(s) of the present disclosure in association with / in the context of low power wake up radio and / or ambient loT (Internet of Things) type device(s) can be possible, in accordance with an embodiment of the invention.

[0087] Fig. 4A to Fig. 4C show schematic diagrams illustrating the flow of information in association with the method of Fig. 3, according to an embodiment of the invention.

[0088] In the example context as shown in Fig. 4A, a gNB (or base station) can, for example, be configured to determine a global model status (e.g. convergence) and / or communicate one or more input signals which can correspond to or be associated with or include a local model update based on the global model status, in accordance with an embodiment of the invention. Moreover, the gNB (or base station) can, for example, be configured to transmit an indication message, which can include the input signal, to one or more User Equipment (UE) whether to enable or disable the local model update reporting by the particular UE, in accordance with an embodiment of the invention.

[0089] In the example context as shown in Fig. 4B, one or more UEs can, for example, be configured to receive the indication message, which may include the input signal, of local model update reporting from the base station (or gNB). Subsequently, the UE(s) analyzes the indication message (or input signal) to determine the local model update to the global model. If the indication message (or input signal) is equal to 1 , the UE(s) disables the local model update reporting to the global model. On the other hand, if the indication message (or input signal) is not equal to 1 , the UE(s) enables the local model update reporting to the global model.

[0090] In the example context as shown in Fig. 4C, the base station BS (or gNB) sends the downlink message to the set of UEs having the Federated Learning model for local model update reporting. The UE’s local model update reporting from the set of UEs comprising the AIML Federated Learning (FL) model can be enabled or disabled by the gNB (or base station) for each UE based on the global model performance status. If reporting is enabled, the UEs that are part of the AIML FLmodel reports the local model update to the global model at the base station (or gNB). In this way, signaling overhead can be reduced for the global model training phase, in accordance with an embodiment of the invention.

[0091] In the foregoing manner, various embodiments of the disclosure are described for addressing at least one of the foregoing disadvantages. Such embodiments are intended to be encompassed by the following claims and are not to be limited to specific forms or arrangements of parts so described and it will be apparent to one skilled in the art in view of this disclosure that numerous changes and / or modification can be made, which are also intended to be encompassed by the following claims.

Claims

Claim(s)1 . A method (300) for training a global model, the method comprising: determining a global model status; transmitting at least one signal for a local model update based on the global model status; and determining the local model update to the global model based on the at least one signal.

2. The method (300) according to claim 1 , further comprising: receiving the at least one signal associated with the local model update; and analyzing the at least one signal to determine the local model update to the global model.

3. The method (300) according to claim 1 , wherein the global model is an Artificial Intelligence / Machine Learning (AIML) Federated Learning model.

4. The method (300) according to claim 1 , wherein the global model status comprises a model maturity condition based on a convergence threshold.

5. The method (300) according to claim 4, wherein the convergence threshold comprises at least one of: model performance accuracy, dataset capabilities and / or model configuration parameters associated with a User Equipment (UE).

6. The method (300) according to claim 1 , wherein transmitting the at least one signal comprises transmitting via at least one of: User Equipment (UE) specific message, UE capability message associated with dataset capabilities of the UE and / or Medium Access Control Control Element (MAC CE).

7. The method (300) according to claim 4, wherein determining the local model update to the global model comprises: enabling the local model update to the global model if the convergence threshold is not met; ordisabling the local model update to the global model if the convergence threshold is met.

8. The method (300) according to claim 1 , further comprising: transmitting the local model update to the global model via a measurement report associated with dataset capabilities of a User Equipment (UE).

9. A computer program comprising instructions which, when the program is executed by a computer, cause the computer to carry out the method (300) according to any of the preceding claims.

10. A computer readable storage medium having data stored therein representing software executable by a computer, the software including instructions, when executed by the computer, to carry out the method (300) according to any one of claims 1-8.

11. An apparatus (102) for training a global model comprising: a first module (202) configured to receive at least one signal associated with a local model update; a second module (204) configured to at least one of process and facilitate the method (300) of claim 1 to claim 8 to generate at least one output signal; and a third module (206) configured to communicate at least one output signal, wherein the output signal corresponds to a control signal for training the global model based on the determination of the local model update to the global model.

12. The apparatus (102) according to claim 11 , wherein the apparatus (102) corresponds to a User Equipment (UE) communicable with a device (104) corresponding to a base station, and wherein the base station corresponds to a Next generation Node B (gNB) configured to receive the at least one output signal from the UE.

13. A system (100) comprising: at least one apparatus (102) according to any of claims 11 and 12; and at least one device (104) according to claim 12, wherein the apparatus (102) and the device (104) are capable of being coupled via at least one of wired coupling and wireless coupling.

Images