Electronic device for federated learning server, and electronic device for core network

Abstract

An electronic device for a federated learning server, and an electronic device for a core network The electronic device for a federated learning server comprises at least one processor and at least one memory, wherein the at least one memory comprises a computer program code, and the at least one memory and the computer program code are configured to enable, by means of the at least one processor, the electronic device to: send to a core network order-of-magnitude information of the order of magnitude of a parameter of a global model for federated learning, so as to assist the core network in identifying from among a plurality of federated learning clients a federated learning client, which cannot upload all of the parameters of a local model of the federated learning client, as a partial upload client, and aggregate, when a preset condition is met, some of the parameters of the local model that are received from the partial upload client, so as to obtain the global model in the current round of training of federated learning.

Description

Electronic devices for federated learning servers and electronic devices for core networks

[0001] This application claims priority to the Chinese patent application filed with the China Patent Office on December 20, 2023, with application number 202311763059.1 and invention name “Electronic device for federated learning server and electronic device for core network”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present disclosure relates to the field of wireless communication technologies, and more particularly to electronic devices for a federated learning server, a core network, and a federated learning client. More particularly, the present disclosure relates to electronic devices for a federated learning server, a core network, and a federated learning client that implement federated learning of partial parameters based on a local model. Background Art

[0003] With the continuous growth of intelligent terminal services, the requirements for wireless networks to support intelligent models are becoming increasingly higher. Typically, user equipment (UE) has different data sets, and UEs are reluctant to share their data sets due to information privacy issues, resulting in data barriers. In addition, UE-specific data sets are often small in size, making it difficult to support the training of more accurate and generalized machine learning (ML) models. Based on this, federated learning (FL) breaks the data barrier problem between UEs through a training mode in which the FL client (e.g., UE) trains a local model locally, the FL server aggregates the local models of multiple FL clients into a global model, and distributes the global model to FL clients. This allows for the training of ML models with high accuracy and strong generalization.

[0004] Summary of the Invention

[0005] A brief overview of the present invention is provided below to provide a basic understanding of certain aspects of the present invention. It should be understood that this overview is not an exhaustive overview of the present invention. It is not intended to identify key or important aspects of the present invention, nor is it intended to limit the scope of the present invention. Its purpose is simply to present certain concepts in a simplified form as a prelude to the more detailed description discussed later.

[0006] According to one aspect of the present disclosure, an electronic device for a federated learning server is provided, the electronic device comprising at least one processor and at least one memory, the at least one memory comprising computer program code, wherein the at least one memory and the computer program code are configured to, through the at least one processor, enable the electronic device to execute: sending magnitude information about the magnitude of parameters of a global model used for federated learning to a core network to assist the core network in identifying a federated learning client that cannot upload all parameters of its local model as a partial uploading client from a plurality of federated learning clients, and, when predetermined conditions are met, performing aggregation based on the partial parameters of the local model received from the partial uploading client to obtain a global model in a current round of training of the federated learning.

[0007] According to one aspect of the present disclosure, an electronic device for a core network is provided, which includes at least one processor and at least one memory, the at least one memory including computer program code, wherein the at least one memory and the computer program code are configured to, through the at least one processor, enable the electronic device to execute: receiving magnitude information about the magnitude of parameters of a global model used for federated learning from a federated learning server, so as to identify a federated learning client that cannot upload all parameters of its local model from a plurality of federated learning clients as a partial uploading client, so that when a predetermined condition is met, the federated learning server aggregates the partial parameters of the local model received from the partial uploading client to obtain a global model in a current round of training of the federated learning.

[0008] According to one aspect of the present disclosure, an electronic device for a federated learning client is provided, the electronic device comprising at least one processor and at least one memory, the at least one memory comprising computer program code, wherein the at least one memory and the computer program code are configured to enable the electronic device to execute, through the at least one processor: when predetermined conditions are met, sending partial parameters of a local model for federated learning to a federated learning server, so that the federated learning server aggregates the local model based on the partial parameters to obtain a global model in a current round of training of the federated learning, wherein the federated learning server sends magnitude information about the parameter magnitudes of the global model to a core network to assist the core network in identifying the electronic device as a partial upload client that cannot upload all parameters of its local model.

[0009] According to one aspect of the present disclosure, a method for a federated learning server is provided, comprising: sending magnitude information about parameter magnitudes of a global model used for federated learning to a core network to assist the core network in identifying a federated learning client that cannot upload all parameters of its local model from among multiple federated learning clients as a partial uploading client, and, when predetermined conditions are met, aggregating the partial parameters of the local model received from the partial uploading client to obtain a global model in a current round of training of the federated learning.

[0010] According to one aspect of the present disclosure, a method for a core network is provided, comprising: receiving magnitude information about parameter magnitudes of a global model used for federated learning from a federated learning server, so as to identify a federated learning client that cannot upload all parameters of its local model from a plurality of federated learning clients as a partial uploading client, so that when predetermined conditions are met, the federated learning server aggregates the partial parameters of the local model received from the partial uploading client to obtain a global model in a current round of training of the federated learning.

[0011] According to one aspect of the present disclosure, a method for a federated learning client is provided, comprising: when predetermined conditions are met, sending partial parameters of a local model for federated learning to a federated learning server, so that the federated learning server aggregates the local model based on the partial parameters to obtain a global model in a current round of training of the federated learning, wherein the federated learning server sends magnitude information about the parameter magnitudes of the global model to a core network to assist the core network in identifying the federated learning client as a partial upload client that cannot upload all parameters of its local model.

[0012] According to other aspects of the present invention, there are also provided computer program codes and computer program products for implementing the above methods, as well as computer-readable storage media having the computer program codes for implementing the above methods recorded thereon. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to further illustrate the above and other advantages and features of the present invention, the following is a further detailed description of specific embodiments of the present invention in conjunction with the accompanying drawings. The accompanying drawings, together with the detailed description below, are included in this specification and form a part of this specification. Elements with the same function and structure are represented by the same reference numerals. It should be understood that these drawings only depict typical examples of the present invention and should not be regarded as limiting the scope of the present invention. In the drawings:

[0014] FIG1 shows a schematic diagram of federated learning in a vehicle network scenario in the prior art;

[0015] FIG2 shows a functional module block diagram of an electronic device for a federated learning server according to an embodiment of the present disclosure;

[0016] FIG3 is a diagram illustrating an example of a neural network model;

[0017] FIG4 is a schematic diagram illustrating clustering using the K-Means algorithm according to an embodiment of the present disclosure;

[0018] FIG5 is a schematic diagram illustrating uploading of some parameters according to an embodiment of the present disclosure;

[0019] FIG6 is a schematic diagram of a lightweight federated learning model training process according to an embodiment of the present disclosure;

[0020] FIG7 is another schematic diagram of a lightweight federated learning model training process according to an embodiment of the present disclosure;

[0021] FIG8 shows a functional module block diagram of an electronic device for a core network according to another embodiment of the present disclosure;

[0022] FIG9 shows a functional module block diagram of an electronic device for a federated learning client according to another embodiment of the present disclosure;

[0023] FIG10 shows a flowchart of a method for a federated learning server according to one embodiment of the present disclosure;

[0024] FIG11 shows a flowchart of a method for a core network according to another embodiment of the present disclosure;

[0025] FIG12 shows a flowchart of a method for a federated learning client according to yet another embodiment of the present disclosure;

[0026] FIG13 is a block diagram showing a first example of a schematic configuration of an eNB or gNB to which the technology of the present disclosure may be applied;

[0027] FIG14 is a block diagram illustrating a second example of a schematic configuration of an eNB or gNB to which the technology of the present disclosure may be applied;

[0028] FIG15 is a block diagram showing an example of a schematic configuration of a smartphone to which the technology of the present disclosure can be applied;

[0029] FIG16 is a block diagram showing an example of a schematic configuration of a car navigation device to which the technology of the present disclosure can be applied; and

[0030] 17 is a block diagram of an exemplary structure of a general-purpose personal computer in which the method and / or apparatus and / or system according to the embodiments of the present invention may be implemented. DETAILED DESCRIPTION

[0031] Exemplary embodiments of the present invention are described below with reference to the accompanying drawings. For the sake of clarity and conciseness, not all features of an actual implementation are described in this specification. However, it should be understood that in the process of developing any such actual implementation, many implementation-specific decisions must be made in order to achieve the developer's specific goals, such as meeting system and business-related constraints, which may vary from implementation to implementation. Furthermore, it should be understood that while development work may be complex and time-consuming, it will be a routine task for those skilled in the art who benefit from this disclosure.

[0032] It is also necessary to explain here that, in order to avoid obscuring the present invention due to unnecessary details, the accompanying drawings only show the device structure and / or processing steps that are closely related to the solution according to the present invention, while other details that are not closely related to the present invention are omitted.

[0033] FIG1 shows a schematic diagram of federated learning in a vehicle network scenario in the prior art.

[0034] As shown in Figure 1, during the FL training process, within a certain communication range, multiple FL clients (for example, FL client 1 to FL client 7 shown in Figure 1) locally train local models and upload them to the FL server. The FL server aggregates all local models and obtains a global FL model to complete the FL model training.

[0035] In this application, the IoV scenario is used as an example for description, but this application is not limited to the IoV. This application can be applied to all scenarios where FL is used for model training. In the following description, for example, in the IoV scenario, the FL server is deployed on the base station and has an AF (application function), and the FL client is a mobile vehicle (UE).

[0036] Because FL models have large parameter sizes, uploading all local model parameters by the FL client increases communication overhead. Therefore, this application proposes lightweight FL model training, where the FL client only uploads a subset of local model parameters. Lightweight FL model training is initiated by the FL server.

[0037] According to one embodiment of the present disclosure, an electronic device 2000 for a federated learning server is provided, which includes at least one processor and at least one memory, the at least one memory including computer program code, wherein the at least one memory and the computer program code are configured to enable the electronic device 2000 to execute, through the at least one processor: sending magnitude information about the magnitude of parameters of a global model used for federated learning to a core network to assist the core network in identifying a federated learning client that cannot upload all parameters of its local model from a plurality of federated learning clients as a partial uploading client, and when predetermined conditions are met, performing aggregation based on the partial parameters of the local model received from the partial uploading client to obtain a global model in a current round of training of the federated learning.

[0038] FIG2 shows a functional module block diagram of an electronic device 2000 for a federated learning server according to an embodiment of the present disclosure.

[0039] As shown in Figure 2, the electronic device 2000 used as an FL server includes: a server control unit 2001, which performs control; a processing unit 2003, which can be configured to send magnitude information about the parameter magnitudes of the global model used for federated learning to the core network under the control of the server control unit 2001, so as to assist the core network in identifying the federated learning client that cannot upload all the parameters of its local model from multiple federated learning clients as a partial uploading client; and an aggregation unit 2005, which can be configured to aggregate based on the partial parameters of the local model received from the partial uploading client under the control of the server control unit 2001 when predetermined conditions are met to obtain the global model in the current round of training of the federated learning.

[0040] The server control unit 2001 can be implemented as one or more processing circuits and at least one memory. The processing circuit can be implemented as a processor or chip, for example. The at least one memory can be RAM, ROM, etc., and is used to store computer program code and data required for the processing circuit to perform processing. The processing unit 2003 and the aggregation unit 2005 can perform operations under the control of the server control unit 2001. It should be understood that the various functional units in the electronic device 2000 shown in Figure 2 are merely logical modules divided according to the specific functions they implement, and are not intended to limit specific implementation methods.

[0041] The electronic device 2000 can be set on the base station side or can be communicatively connected to the base station. The electronic device 2000 can be set on the road side unit (RSU) side or can be communicatively connected to the RSU. The electronic device 2000 can be set on the mobile edge computing (MEC) side or can be communicatively connected to the MEC. For example, the electronic device 2000 can work as one of the base station, RSU, and MEC itself, and can also include external devices such as memory and transceiver (not shown). The memory can be used to store programs and related data information that need to be executed by the electronic device 2000 to implement various functions. The transceiver may include one or more communication interfaces to support communication with different devices (for example, UE, base station, RSU, MEC, etc.), and the implementation form of the transceiver is not specifically limited here.

[0042] As an example, the base station may be, for example, an eNB or a gNB.

[0043] As an example, the core network may be, for example, a Network Data Analysis Function (NWDAF) network element.

[0044] The wireless communication system according to the present disclosure may be a 5G NR (New Radio) communication system, a 5G+ communication system, or a 6G communication system. Furthermore, the wireless communication system according to the present disclosure may include a non-terrestrial network (NTN). Optionally, the wireless communication system according to the present disclosure may also include a terrestrial network (TN). Furthermore, those skilled in the art will appreciate that the wireless communication system according to the present disclosure may also be a 4G or 3G communication system.

[0045] For example, a partial uploading client is a FL client that cannot upload all parameters of its local model due to poor channel quality.

[0046] For example, the aforementioned multiple federated learning clients are all clients participating in federated learning.

[0047] As shown in Figure 1, the prior art example of federated learning in a vehicle-to-vehicle network scenario shows, if the FL client uploads all of its model parameters during each training iteration, significant communication overhead will be incurred. Furthermore, if some FL clients are unable to upload all parameters of their local models, forcing them to do so can easily lead to transmission errors during the upload process. This can cause errors in the local models received by the FL server, further compromising the accuracy of the global model.

[0048] According to an embodiment of the present disclosure, the electronic device 2000 sends magnitude information about the parameter magnitudes of the global model to the core network to assist the core network in identifying some uploading clients, so that the some uploading clients only need to upload some model parameters during the local model uploading process, thereby reducing the communication overhead of FL model training and will not affect the accuracy of the global model.

[0049] Hereinafter, the electronic device 2000 is sometimes referred to as an FL server.

[0050] For example, when the above-mentioned predetermined conditions are met, the electronic device 2000 aggregates partial parameters of the local model uploaded by the partial upload client and all parameters of the local model uploaded by the non-partial upload client to obtain the global model in the current round of training of federated learning.

[0051] For example, when the predetermined conditions are not met, the above-mentioned multiple federated learning clients upload all parameters of the local model to the electronic device 2000, and the electronic device 2000 aggregates all parameters of the received local model to obtain the global model in the current round of training of federated learning.

[0052] As an example, the magnitude information (hereinafter sometimes referred to as the model parameter magnitude) includes information about the size of the parameters of the global model (which may be simply referred to as the model size). Those skilled in the art may also conceive of other examples of magnitude information, which will not be repeated here.

[0053] For example, an untrusted FL server sends the magnitude information to the NWDAF network element through a Network Exposure Function (NEF) network element, while a trusted FL server directly sends the magnitude information to the NWDAF network element.

[0054] As an example, the magnitude information is used as an input to the UE communication analysis in the NWDAF, and the UE communication prediction output of the UE communication analysis includes a list with IDs of partially uploaded clients.

[0055] For UE Communication Analytics in NWDAF, refer to section 6.7.3 of 3GPP TS 23.288. For example, magnitude information can be placed in the input of the service, and a list of FL clients that cannot upload all model parameters can be placed in the UE Communication Predictions output of the service.

[0056] For example, the new input parameters can be as follows:

[0057] For example, the new output parameter can be as follows:

[0058] As an example, the predetermined conditions include receiving a list of partial uploading clients from the core network and / or the accuracy of the global model in the previous round of training reaches a preset accuracy, wherein the list includes the IDs of the partial uploading clients, and when the accuracy of the global model in the previous round of training reaches the preset accuracy, multiple federated learning clients are used as partial uploading clients.

[0059] For example, after the NWDAF network element determines that some FL clients cannot upload all the parameters of their local models due to poor channel quality and thus determines the partial uploading clients, it stores the IDs of the partial uploading clients in a list and sends the list to the FL server to assist the FL server in subsequently notifying these partial uploading clients to upload only partial parameters.

[0060] For example, once the global model reaches a preset accuracy, uploading all local model parameters is no longer necessary; only the model parameters that most need to be updated can be uploaded. For example, those skilled in the art can pre-set the preset accuracy based on experience or application scenarios. For example, the preset accuracy could be 95%, 80%, and so on. These details are not repeated here.

[0061] For example, if the accuracy of the global model in the previous round of training reaches the preset accuracy, all multiple federated learning clients are considered to be partial upload clients. For example, if the list is empty and the accuracy of the global model in the previous round of training reaches the preset accuracy, even if there is no federated learning client that cannot upload all the parameters of its local model, all multiple federated learning clients are considered to be partial upload clients. In addition, if the accuracy of the global model in the previous round of training reaches the preset accuracy, the method for determining partial parameters is the same as the method for determining partial parameters in the case of an FL client that cannot upload all the parameters of its local model due to poor channel quality. The method for determining partial parameters will be described in detail below.

[0062] As shown in Figure 1, the prior art example of federated learning in a vehicle-to-vehicle network scenario shows, due to the large number of model parameters, requiring the client to upload all local model parameters increases communication overhead. In particular, when the channel quality of some FL clients is poor and / or the global model has already reached a predetermined accuracy, requiring the FL client to upload all local model parameters further increases communication overhead. Furthermore, when the channel quality of some FL clients is poor, forcibly uploading all the parameters of these FL clients' local models can easily lead to transmission errors during the upload process. This can cause errors in the local models received by the FL server, thereby compromising the accuracy of the global model. For example, in Figure 1, if the channel between FL client 2 and FL client 7 suddenly deteriorates, forcing the upload of all local model parameters will result in large errors in the local models received by the FL server, further weakening the performance of the global model.

[0063] In contrast, in embodiments of the present disclosure, when the FL server receives a list of FL clients that are unable to upload all model parameters, the FL server triggers lightweight FL model training (i.e., some of the uploading clients only upload some parameters of their local model). This not only reduces communication overhead but also reduces the error of the local model received by the FL server, thereby maintaining the accuracy of the global model. When the global model accuracy of the FL server reaches a preset accuracy (model accuracy threshold), lightweight FL model training is performed, which not only reduces communication overhead but also maintains the accuracy of the global model.

[0064] When the global model reaches the preset accuracy, the accuracy difference between each iteration of FL training is not particularly large, so lightweight FL model training, that is, uploading some parameters of the local model, can be periodically triggered. When the FL client communication quality is poor, since each FL training iteration requires the client to upload its local model, the FL client communication quality must be predicted in each FL training iteration to determine whether the FL client can upload all its local model parameters. For example, data transmission between the 5G core network (5GC) and the FL server does not occupy wireless communication resources and does not incur significant communication overhead. Therefore, in this case, lightweight FL model training can be triggered in real time.

[0065] When the list of FL clients returned by the NWDAF network element is empty and the accuracy of the current global model does not reach the preset accuracy, the FL server sends a notification to the FL client to upload all parameters of the local model.

[0066] As an example, the IDs of some uploading clients included in the above list are determined by the core network based on magnitude information and predicted channel information between the electronic device 2000 and the federated learning client.

[0067] For example, the NWDAF network element has the function of predicting the channel information between the FL server and the FL client (for example, the base station and the UE). The NWDAF network element uses the above-mentioned predicted information and the magnitude information of the received model parameters to determine whether the FL client can upload all the parameters of its local model to the FL server under the current communication conditions.

[0068] As an example, the channel information includes at least one of a channel quality indication (CQI), a precoding matrix indication (PMI), a reference signal received power (RSRP), and a signal-to-noise ratio (SNR) of the channel between the electronic device 2000 and the federated learning client.

[0069] For example, the NWDAF network element calculates the transmission rate based on the SNR and bandwidth information between the FL server and the FL client. It also calculates the amount of data that can be uploaded within the transmission delay limit of the FL local model upload based on the above delay limit, and then determines whether the FL client can upload all the parameters of its local model.

[0070] In expression (1), SNR is the SNR value of the channel between the FL server and the FL client, B is the bandwidth allocated by the FL server to the FL client, Delay is the upper limit of the FL local model upload transmission delay limited by the FL server, S l is the amount of data that the FL client can support uploading, S g is the amount of data for the parameters of the FL global model. By comparing S l With S g It can determine whether the FL client can upload all the parameters of the local model, and what proportion of model parameters can be uploaded if it cannot upload all the parameters of the local model. From expression (1), it can be seen that in S l Greater than S g In the case of S, it is determined that the FL client can upload all the parameters of its local model to the FL server under the current communication situation; l Less than S g In the case of , it is determined that the FL client cannot upload all the parameters of its local model to the FL server under the current communication situation.

[0071] As an example, the processing unit 2003 can be configured to calculate, for the parameters of the global model in the previous round of training and the parameters of the local models uploaded by multiple federated learning clients in the previous round of training: a local model parameter deviation degree representing the degree of dispersion between the parameters of the local models of the multiple federated learning clients, and a global model parameter deviation degree representing the degree of deviation between the parameters of the local models of the multiple federated learning clients and the parameters of the global model, and determine partial parameters based on the local model parameter deviation degree and the global model parameter deviation degree. In other words, the electronic device 2000 can determine the parameters that need to be supplemented in the global model in the current round of training (i.e., determine the partial parameters that some uploading clients need to upload in the current round of training) based on the local model parameters of the FL clients received in the previous round of iterations.

[0072] As an example, the processing unit 2003 can be configured to calculate the average value of the i-th parameter based on the i-th parameter of the local models of multiple federated learning clients, and calculate the degree of local model parameter deviation for the i-th parameter based on the difference between the i-th parameter of the local model of each federated learning client and the average value; and calculate the degree of global model parameter deviation for the i-th parameter based on the difference between the i-th parameter of the local model of each federated learning client and the i-th parameter of the global model.

[0073] For example, the FL server calculates the degree of local model parameter deviation for the i-th parameter based on the i-th parameter of the local model uploaded by the FL client in the previous iteration:

[0074] In expression (2), N represents the number of multiple FL clients, represents the i-th parameter of the n-th FL client (n is a positive integer greater than or equal to 1 and less than or equal to N), represents the average value of the i-th parameter in the local models of all N FL clients.

[0075] As mentioned above, σ l It measures the dispersion of local model parameters across multiple FL clients. For example, the greater the dispersion of all FL clients for the i-th parameter, the greater the need for further updating of that parameter, i.e., the greater the probability that that parameter of the local model will be uploaded to the FL server.

[0076] For example, the FL server calculates the i-th parameter of the local model and the i-th parameter p of the global model uploaded by the FL client in the previous iteration. g (i) to calculate the global model parameter deviation for the i-th parameter:

[0077] As mentioned above, σ g It measures the average gap between the local model parameters of all FL clients and the global model parameters. For example, for the i-th parameter in the model, the larger the average gap between the i-th parameter in the local models of all FL clients and the i-th parameter in the global model, the greater the need for further update of this parameter, that is, the greater the probability that this parameter will be uploaded to the FL server.

[0078] If there is an FL client among N FL clients that did not upload the i-th parameter in the previous round of training, then the FL client that did not upload the i-th parameter is 0.

[0079] As an example, the processing unit 2003 can be configured to cluster the parameters using a clustering method based on the degree of local model parameter deviation and the degree of global model parameter deviation, thereby obtaining multiple clusters after clustering, and selecting a selected cluster that meets the predetermined cluster conditions from the multiple clusters, and using the parameters in the selected cluster as partial parameters.

[0080] For example, the global model and the local model are layered neural network models. Generally, for a neural network model, the parameters of the neural network refer to weight values ​​and bias values.

[0081] FIG3 is a diagram showing an example of a neural network model. As shown in FIG3 , the circles in the first column represent neurons in the input layer, the circles in the last column represent neurons in the output layer, the circles between the first and last columns represent neurons in the hidden layer, the lines between neurons represent weight values, and each neuron has a bias value. Taking the first two layers of neurons in FIG3 as an example, the index of each neuron is the value in its circle (the index of the neuron can also be defined in other ways, as long as each neuron can be uniquely identified). For example, the weight value between neuron 1 and neuron 6 is named ω 1，6 , the weight value between neuron 5 and neuron 11 is named ω 5，11 , the weight values ​​between two different neurons are named in the same way. Taking the neuron with index 6 as an example, the value of the neuron is calculated as shown in the following expression (4): x6=(ω 1，6 x1+ω 2，6 x2+ω 3，6 x3+ω 4，6 x4+ω 5，6 x5)+b6 Expression (4)

[0082] In expression (4), ω is a weight value, and b is a bias value.

[0083] As can be seen from the above description, the number of weights and biases in the neural network model is huge. If the weights and biases are calculated and clustered to determine the degree of deviation of local model parameters and the degree of deviation of global model parameters, the amount of calculation is large. Therefore, in this application, the global model and all uploaded local models are processed as all-1 inputs on the FL server side. Specifically, all input values ​​are set to 1, for example, [1,1,1,1,…], and these values ​​are input into the global model and all uploaded local models to obtain the value of each neuron in the model (for the calculation process of the neuron value, see the above expression (4) for neuron 6). Therefore, the parameters of the model described in this application refer to the values ​​of the neurons in the FL model.

[0084] As an example, the predetermined cluster condition includes that the probability of selection corresponding to the cluster is greater than the predetermined probability, and the processing unit 2003 can be configured to use the local model parameter deviation degree and the global model parameter deviation degree as the coordinates of a two-dimensional coordinate system, respectively, and use the local model parameter deviation degree and the global model parameter deviation degree corresponding to the calculated parameter as the coordinate value, so that each parameter is represented as a point in the coordinate system, and all points in the coordinate system are clustered using the K-Means algorithm to obtain multiple clusters, and for each cluster in at least a part of the multiple clusters, based on the distance between the cluster center and the coordinate origin, and the angle between the line from the cluster center to the coordinate origin and the dividing line of the first quadrant of the coordinate system, the probability of selection of the cluster is calculated, wherein the dividing line is a straight line passing through the coordinate origin and at a predetermined angle to the horizontal axis of the first quadrant, wherein, as the distance increases, the probability of selection increases, and as the angle decreases, the probability of selection increases.

[0085] For example, those skilled in the art may predetermine the predetermined probability and the predetermined angle based on experience or application scenarios.

[0086] The samples in the K-Means algorithm are defined as parameters (i.e., points in the above coordinate system) expressed in terms of the degree of deviation of local model parameters and the degree of deviation of global model parameters. The specific steps for clustering all points in the above coordinate system using the K-Means algorithm are as follows:

[0087] Step a: Randomly select K points in the sample as cluster centers (cluster centroids);

[0088] Step b: Calculate the distances between other samples in the sample and the K cluster centers respectively, and classify these samples into the category of the cluster center closest to them;

[0089] Step c: Calculate the average value of each category for the clustered samples and solve the new cluster centroid;

[0090] Step d: Compare the K cluster centroids calculated with the previous one. If the cluster centroids have changed, go to step b, otherwise go to step e.

[0091] Step e: When the centroid no longer changes, stop the iteration and output the clustering results.

[0092] Step f: Select a cluster from the clustering results, and use the parameters in the selected cluster as partial parameters.

[0093] FIG4 is a schematic diagram illustrating clustering using the K-Means algorithm according to an embodiment of the present disclosure.

[0094] In Figure 4, for example, the degree of deviation of local model parameters σ l is the horizontal axis, the degree of deviation of global model parameters σ g Establish a coordinate system for the vertical axis. Given that all parameters in the FL model have σ l and σ g Therefore, each parameter in the FL model is a point in the established coordinate system. All parameters in the FL are represented in the established coordinate system, and the model parameters are clustered with the help of the K-Means algorithm. The clustering results are shown in the circles in Figure 4 (for example and not limitation, Figure 4 shows that the clustering results include cluster 1, cluster 2, and cluster 3), and each cluster has a cluster center.

[0095] In the following description, for simplicity, it is assumed that the predetermined angle is 45 。 For description, the above-mentioned dividing line is a straight line that forms a 45-degree angle with the horizontal axis of the first quadrant.

[0096] For example, the expression for calculating the probability of a cluster being selected is as follows:

[0097] In expression (5), K represents the total number of clusters in the clustering result (in FIG. 4 , for example, K=3), k represents the kth cluster (in FIG. 4 , for example, k is 1 to 3), P(k) represents the probability of selecting the kth cluster, d(k) represents the distance from the cluster center of the kth cluster to the coordinate origin o (in FIG. 4 , d(1), d(2), and d(3) are shown), θ(k) represents the deviation angle between the line connecting the cluster center of the kth cluster and the coordinate origin and the x-axis (in FIG. 4 , θ(3) is shown), and g(·) represents the normalization function.

[0098] In the embodiment according to the present disclosure, there are two principles for cluster selection: one is to select a cluster whose cluster center is far from the coordinate origin (to ensure σ l and σ gThe comprehensive value of is large), so d(k) is considered in expression (5); secondly, a cluster is selected with a small angle between the line connecting the cluster center to the coordinate origin and the dividing line of the first quadrant of the coordinate system (for example, a straight line at a 45-degree angle to the x-axis, as shown by the dotted line in Figure 4) (to ensure that σ l and σ g The values ​​are all large, and there will be no extreme situation of bias to one side, such as avoiding the cluster center on the x-axis and far away from the coordinate origin). Therefore, |θ(k)-45°| is considered in the cluster selection expression (5). By calculating the P(k) values ​​of all clusters, clusters are selected based on the P(k) values. For example, all parameters in the cluster with the largest P(k) value can be selected as the partial parameters to be uploaded, that is, the cluster with the largest deviation degree (local model parameter deviation degree σ) is selected. l The degree of deviation from the global model parameters σ g are as large as possible) as part of the parameters that need to be filled.

[0099] Clustering is described above using the K-Means algorithm as an example. However, those skilled in the art may conceive of other clustering methods, which will not be described here.

[0100] As an example, the processing unit 2003 may be configured to send notification information about partial parameters to the partial uploading client, so that the partial uploading client only uploads the partial parameters in the current round of training.

[0101] As described above, the global model is a layered neural network model. As an example, the notification information includes the position information of some parameters in the neural network model. This position information is, for example, the index of the neuron mentioned above.

[0102] As an example, the aggregation unit 2005 can be configured to align partial parameters of the local model received from a partial uploading client and all parameters of the local model received from other clients in a plurality of federated learning clients based on location information, and perform aggregation of the local models.

[0103] FIG5 is a schematic diagram illustrating partial parameter uploading according to an embodiment of the present disclosure.

[0104] After receiving a notification about partial parameter upload (e.g., a list of neuron indices to be uploaded), the FL client uploads some of the model's parameters. For example, Figure 5 shows a neuron to be uploaded (referred to as an "upload neuron" for short). The FL client then uploads the weights of all upper-layer neurons connected to the uploaded neuron, as well as the bias value of the uploaded neuron, to the FL server. After receiving the local models uploaded by all FL clients, the FL server aligns them based on the neuron indices and aggregates them to form a global model.

[0105] In scenarios where FL clients are mobile (e.g., in connected vehicles and drones), some FL clients may leave the FL server's coverage area before completing local model training. Therefore, it may be necessary to offload computations to these clients during each round of FL training.

[0106] For example, the drone scenario can include the following two scenarios: In scenario 1, the drone acts as the FL server and multiple vehicles act as FL clients; in scenario 2, the base station acts as the FL server and multiple drones performing emergency missions, for example, act as FL clients.

[0107] The above problem can be solved by the electronic device 2000 receiving a computation offloading indication triggered by it from the core network. The present disclosure adds a computation offloading analysis function for the NWDAF network element in the 5G core network, that is, when the FL server (e.g., gNB, RSU, MEC, drone, etc.) and the FL client (e.g., UE, drone, etc.) perform each round of FL training iteration, the NWDAF assists in analyzing the residence time of all FL clients within the coverage area of ​​the FL server to determine whether to trigger a computation offloading indication.

[0108] As an example, the processing unit 2003 can be configured to receive a computation offloading indication from the core network, indicating that the federated learning client is to perform computation offloading, and to notify all federated learning clients within the coverage of the electronic device 2000 of the computation offloading indication, so that the federated learning client can determine whether to perform computation offloading, wherein the computation offloading indication is sent by the core network based on the residence time of all federated learning clients within the coverage of the electronic device 2000.

[0109] For example, the above-mentioned residence time may be an average residence time, a median residence time, etc. of all federated learning clients within the coverage area of ​​the electronic device 2000 .

[0110] For example, in computation offloading, a federated learning client transmits the parameters of its local model to other federated learning clients for the other federated learning clients to perform federated learning based on the parameters, and the federated learning client no longer participates in federated learning. For example, other federated learning clients perform local model fusion based on the parameters and the parameters of their local models (e.g., perform a weighted average of the parameters and the parameters of their local models) to perform federated learning based on the fused local models.

[0111] Other federated learning clients perform federated learning based on the fused local model, which can improve the accuracy of federated learning.

[0112] In FL learning, computation offloading can also be called model offloading. In the following, computation offloading is sometimes written as model / computation offloading.

[0113] For example, the FL client ultimately decides whether to offload computation based on whether it has completed the training of the local model.

[0114] As an example, the calculation offloading indication is sent by the core network when it is determined that the dwell time is less than the training duration of the preset local model.

[0115] For example, those skilled in the art may set the training duration of the preset local model based on experience or application scenarios.

[0116] For example, when the core network determines that the dwell time is greater than or equal to the preset training duration of the local model, the computation offloading indication is not triggered.

[0117] Those skilled in the art may also conceive of other examples in which the core network sends a computation offloading indication based on the dwell time, which are not described here.

[0118] As an example, the dwell time is obtained by the core network based on the ID of the electronic device 2000 , a time ID used to characterize time, and the density of federated learning clients within the coverage area of ​​the electronic device 2000 .

[0119] For example, the ID of the electronic device 2000 may be a unique identifier of the electronic device 2000, and the ID of the electronic device 2000 may indicate location information of the electronic device 2000. For example, the ID of the electronic device 2000 may be an IP address of the electronic device 2000.

[0120] For example, the time ID may be a timestamp ID, a time slot ID, etc. For example, the time ID may represent the morning peak, the evening peak, the flat closing time, etc.

[0121] The above density refers to the distribution density of federated learning clients within the coverage area of ​​the electronic device 2000 .

[0122] As an example, the core network also obtains the residence time by using the moving speed of the client through federated learning.

[0123] For example, the moving speed of the federated learning client may be an average moving speed of the federated learning clients within the coverage of the electronic device 2000 , or may be a list of moving speeds of all federated learning clients within the coverage of the electronic device 2000 .

[0124] For example, the core network can obtain the predicted average moving speed of all federated learning clients within the coverage of electronic device 2000 based on a neural network model, using the ID of electronic device 2000, the time ID used to characterize time, and the density of federated learning clients within the coverage of electronic device 2000, and obtain the average residence time based on the predicted average moving speed.

[0125] For example, the neural network model used to obtain the dwell time may be a long short-term memory network (LSTM).

[0126] For example, the input to the computational offloading analysis function (dataset information from AF) is:

[0127]

[0128] For example, the output of the calculation offload analysis function (output analysis) is:

[0129] FIG6 is a schematic diagram of a lightweight FL model training process according to an embodiment of the present disclosure. In FIG6 , it is assumed that the FL server (electronic device 2000 ) is not trusted, and the multiple federated learning clients mentioned above include FL client 1 to FL client N.

[0130] In step 1, the FL server selects FL clients. For example, the FL server selects FL clients based on their needs. For example, if the datasets owned by each FL client are heterogeneous, the FL server selects FL clients based on the value of the datasets to fully train the FL model.

[0131] In step 2, the FL server distributes the initial global model. After selecting the FL client, the FL server distributes the initial global model to the selected FL client for subsequent local model training of the FL client.

[0132] In step 3 (including steps 3a and 3b), the FL server sends a model parameter level notification to the NWDAF network element through the NEF network element. This notification helps the NWDAF network element identify which FL clients are unable to upload all parameters of their local models under the current communication conditions.

[0133] In step 4, the NWDAF network element compares the model parameter magnitudes with the FL client channel quality to determine whether the FL client can upload all parameters of its local model to the FL server under the current communication conditions.

[0134] In step 5 (including steps 5a and 5b), the NWDAF network element sends a list of FL clients that cannot upload all model parameters to the FL server.

[0135] In step 6, the FL server completes and determines the parameters of the partial model. If the predetermined conditions mentioned above are met, the FL server determines the parameters of the partial model that need to be uploaded.

[0136] In step 7, the FL server notifies the client of the upload of the local model (all or part of the model parameters). For example, after the FL server determines the model parameters that need to be uploaded (completed), it notifies the client of which parameters should be uploaded in the current iteration through a notification message that includes the location information of the model parameters to be completed. For example, the notification message is a list containing the indices of the locations of all model parameters that need to be completed. Furthermore, for FL clients that have not yet been notified of the model parameter completion request, all parameters of their local model can be uploaded.

[0137] Optionally, in step a, the FL client performs model / computation offloading. For a description of model / computation offloading, please refer to the description of the calculation offloading analysis function above.

[0138] In step 8, the FL client uploads the local model (all or some model parameters). For example, after receiving a notification to upload a local model (all or some parameters), if some FL clients have poor channel quality, the FL client with the poor channel will upload the corresponding model parameters in the local model based on the location information of the partial parameters to be uploaded, while other FL clients will upload all parameters of their local models. If the global model accuracy reaches a preset model accuracy threshold, all FL clients will upload the corresponding model parameters in the local model based on the location information of the partial parameters. In this case, when uploading partial parameters of the local model, the FL client will upload the parameter value information at the corresponding location based on the parameter location information.

[0139] In step 9, the FL server performs model aggregation. For example, after receiving the local models uploaded by all FL clients, the FL server aligns the local model parameters of the clients based on the location information and parameter value information of the local models and completes global model aggregation.

[0140] In step 10, the FL server updates / terminates the process. For example, based on the requirements of the aggregation task initiator, the FL server decides whether to continue updating or terminate the FL training process.

[0141] In step 11, the FL server distributes the aggregated global model. The FL server distributes the global model aggregated in this round of iteration to the FL client for the next round of local model training of the FL client.

[0142] In step 12, the FL client performs a local model update. After receiving the new global model, the FL client starts a new round of training and updates the local model.

[0143] In each round of training, steps 4 to 12 are iteratively executed.

[0144] FIG7 is another schematic diagram of a lightweight FL model training process according to an embodiment of the present disclosure. In FIG7 , it is assumed that the FL server (electronic device 2000 ) is trusted.

[0145] As described above, the untrusted FL server sends model parameter level notifications to the NWDAF network element via the NEF network element, while the trusted FL server sends model parameter level notifications directly to the NWDAF network element. Therefore, there is no NEF network element in Figure 7, and except for steps 3 and 5, the other steps in Figure 7 are the same as those in Figure 6 and are not repeated here.

[0146] The present disclosure also provides an electronic device 8000 for a core network according to another embodiment of the present disclosure. The electronic device 8000 includes at least one processor and at least one memory, the at least one memory including computer program code, wherein the at least one memory and the computer program code are configured to, through the at least one processor, cause the electronic device 8000 to execute: receiving magnitude information about the magnitude of parameters of a global model used for federated learning from a federated learning server, identifying a federated learning client that cannot upload all parameters of its local model from a plurality of federated learning clients as a partial uploading client, so that, when a predetermined condition is met, the federated learning server aggregates the partial parameters of the local models received from the partial uploading clients to obtain a global model in the current round of federated learning training.

[0147] FIG8 shows a functional module block diagram of an electronic device 8000 for a core network according to another embodiment of the present disclosure.

[0148] As shown in Figure 8, the electronic device 8000 includes: a core network control unit 8001, which performs control; an identification unit 8003, which, under the control of the core network control unit 8001, receives magnitude information about the parameter magnitudes of the global model used for federated learning from the federated learning server, so as to identify the federated learning client that cannot upload all the parameters of its local model from multiple federated learning clients as a partial uploading client, so that when predetermined conditions are met, the federated learning server aggregates the partial parameters of the local model received from the partial uploading client to obtain the global model in the current round of training of the federated learning.

[0149] The core network control unit 8001 can be implemented as one or more processing circuits and at least one memory. The processing circuit can be implemented as a processor or chip, for example. The at least one memory can be RAM, ROM, etc., and the at least one memory is used to store computer program code and data required for the processing circuit to perform processing. The identification unit 8003 can perform operations under the control of the core network control unit 8001. It should be understood that the various functional units in the electronic device 8000 shown in Figure 8 are merely logical modules divided according to the specific functions they implement, and are not intended to limit the specific implementation method.

[0150] For example, the electronic device 8000 may operate as a core network device itself and may also include external devices such as a memory and a transceiver (not shown). The memory may be used to store programs and related data information required for the electronic device 8000 to implement various functions. The transceiver may include one or more communication interfaces to support communication with different devices (e.g., UE, base station, etc.), and the implementation form of the transceiver is not specifically limited here.

[0151] As an example, the federated learning server in the embodiment of the electronic device 8000 may be the electronic device 2000 mentioned above. As an example, the electronic device 8000 may be the core network involved in the embodiment of the electronic device 2000 mentioned above.

[0152] For example, a partial uploading client is a FL client that cannot upload all parameters of its local model due to poor channel quality.

[0153] For example, the aforementioned multiple federated learning clients are all clients participating in federated learning.

[0154] According to an embodiment of the present disclosure, the electronic device 8000 can identify some uploading clients based on the magnitude information of the parameter magnitudes of the global model received from the FL server, so that the some uploading clients only need to upload some model parameters during the local model uploading process, thereby reducing the communication overhead of FL model training and will not affect the accuracy of the global model.

[0155] As an example, the magnitude information is used as an input to the UE communication analysis in the NWDAF, and the UE communication prediction output of the UE communication analysis includes a list with IDs of partially uploaded clients.

[0156] As an example, the magnitude information includes information about the size of the parameters of the global model. Those skilled in the art may also conceive of other examples of magnitude information, which will not be repeated here.

[0157] For example, the electronic device 8000 may be an NWDAF network element. For example, the untrusted FL server sends the magnitude information to the NWDAF network element via the NEF network element. The trusted FL server directly sends the magnitude information to the NWDAF network element.

[0158] As an example, the predetermined conditions include the federated learning server receiving a list of partial uploading clients from the electronic device 8000 and / or the accuracy of the global model in the last round of training reaching a preset accuracy, wherein the list includes the IDs of the partial uploading clients.

[0159] For the description of the predetermined conditions, please refer to the corresponding part in the embodiment of the electronic device 2000, which will not be repeated here.

[0160] As an example, the identification unit 8003 may be configured to determine IDs of some uploading clients included in the list based on the magnitude information and the predicted channel information between the federated learning server and the federated learning client.

[0161] For example, the electronic device 8000 has the function of predicting the channel information between the FL server and the FL client (for example, the base station and the UE). The electronic device 8000 uses the above-mentioned predicted information and the magnitude information of the received model parameters to determine whether the FL client can upload all the parameters of its local model to the FL server under the current communication conditions.

[0162] As an example, the channel information includes at least one of a channel quality indication (CQI), a precoding matrix indication (PMI), a reference signal received power (RSRP), and a signal-to-noise ratio (SNR) of the channel between the electronic device 8000 and the federated learning client.

[0163] For a description of how the electronic device 8000 determines some uploading clients based on the magnitude information and the SNR, please refer to the description of expression (1) in the embodiment of the electronic device 2000, which will not be repeated here.

[0164] As an example, the identification unit 8003 can be configured to send a computation offloading indication to the federated learning server, instructing the federated learning client to perform computation offloading, based on the residence time of all federated learning clients within the coverage of the federated learning server, so that the federated learning server can notify all federated learning clients within its coverage of the computation offloading indication, so that the federated learning client can determine whether to perform computation offloading.

[0165] For example, the above-mentioned residence time may be the average residence time, median residence time, etc. of all federated learning clients within the coverage area of ​​the federated learning server.

[0166] As an example, the identification unit 8003 may be configured to send a calculation offloading indication when it is determined that the dwell time is less than a preset training duration of the local model.

[0167] As an example, the identifying unit 8003 may be configured to obtain the residence time based on the ID of the federated learning server, a time ID used to characterize time, and the density of federated learning clients within the coverage area of ​​the federated learning server.

[0168] As an example, the identification unit 8003 may be configured to obtain the dwell time further based on the moving speed of the federated learning client.

[0169] For the description of model / computation offloading, please refer to the description of the calculation offloading analysis function in the electronic device 2000 embodiment above, which will not be repeated here.

[0170] The present disclosure also provides an electronic device 9000 for a federated learning client according to another embodiment of the present disclosure. The electronic device 9000 includes at least one processor and at least one memory, the at least one memory including computer program code, wherein the at least one memory and the computer program code are configured to, through the at least one processor, cause the electronic device 9000 to execute: when a predetermined condition is met, sending partial parameters of a local model for federated learning to a federated learning server, so that the federated learning server aggregates the local model based on the partial parameters to obtain a global model in the current round of federated learning training, wherein the federated learning server sends magnitude information about the magnitude of the parameters of the global model to the core network to assist the core network in identifying the electronic device 9000 as a partial upload client that cannot upload all the parameters of its local model.

[0171] FIG9 shows a functional module block diagram of an electronic device 9000 for a federated learning client according to another embodiment of the present disclosure.

[0172] As shown in Figure 9, the electronic device 9000 includes: a client control unit 9001, which performs control; a communication unit 9003, which, under the control of the client control unit 9001, sends partial parameters of the local model used for federated learning to the federated learning server when predetermined conditions are met, so that the federated learning server can aggregate the local model based on the partial parameters to obtain the global model in the current round of training of federated learning, wherein the federated learning server sends magnitude information about the parameter magnitude of the global model to the core network to assist the core network in identifying the electronic device 9000 as a partial upload client that cannot upload all parameters of its local model.

[0173] The client control unit 9001 can be implemented as one or more processing circuits and at least one memory. The processing circuit can be implemented as a processor or chip, for example. The at least one memory can be RAM, ROM, etc., and is used to store computer program code and data required for the processing circuit to perform processing. The communication unit 9003 can perform operations under the control of the client control unit 9001. It should be understood that the various functional units in the electronic device 9000 shown in Figure 9 are merely logical modules divided according to the specific functions they implement, and are not intended to limit specific implementation methods.

[0174] For example, the electronic device 9000 may operate as a user device itself and may also include external devices such as a memory and a transceiver (not shown). The memory may be used to store programs and related data information required for the user device to implement various functions. The transceiver may include one or more communication interfaces to support communication with different devices (e.g., base stations, other user devices, etc.), and the implementation form of the transceiver is not specifically limited here.

[0175] As an example, the federated learning server in the embodiment of electronic device 9000 may be the electronic device 2000 mentioned above, and the core network in the embodiment of electronic device 9000 may be the electronic device 8000 mentioned above. As an example, electronic device 9000 may be part of the upload client involved in the embodiments of electronic devices 2000 and 8000 mentioned above.

[0176] For example, electronic device 9000 is an FL client that cannot upload all parameters of its local model due to poor channel quality.

[0177] According to the embodiment of the present disclosure, the electronic device 9000 only needs to upload part of the model parameters during the local model uploading process, thereby reducing the communication overhead of FL model training and not affecting the global model accuracy.

[0178] As an example, the magnitude information is used as an input to the UE communication analysis in the NWDAF, and the UE communication prediction output of the UE communication analysis includes a list with IDs of partially uploaded clients.

[0179] As an example, the magnitude information includes information about the size of the parameters of the global model. Those skilled in the art may also conceive of other examples of magnitude information, which will not be repeated here.

[0180] As an example, the predetermined condition includes that the federated learning server receives a list including IDs of some uploading clients from the core network and / or the accuracy of the global model in the previous round of training reaches a preset accuracy.

[0181] For the description of the predetermined conditions, please refer to the corresponding part in the embodiment of the electronic device 2000, which will not be repeated here.

[0182] As an example, the communication unit 9003 may be configured to receive notification information about some parameters from the federated learning server.

[0183] As an example, the global model is a hierarchical neural network model, and the notification information includes position information of some parameters in the neural network model.

[0184] For a description of the location information of some parameters in the neural network model, please refer to the corresponding part in the embodiment of the electronic device 2000, which will not be repeated here.

[0185] As an example, the communication unit 9003 can be configured to receive a computation offloading indication from the federated learning server, indicating that the federated learning client is to perform computation offloading, for determining whether to perform computation offloading, wherein the computation offloading indication is sent by the core network to the federated learning server based on the residence time of all federated learning clients within the coverage area of ​​the federated learning server.

[0186] For example, the above-mentioned residence time may be the average residence time, median residence time, etc. of all federated learning clients within the coverage area of ​​the federated learning server.

[0187] As an example, the calculation offloading indication is sent by the core network when it is determined that the dwell time is less than the training duration of the preset local model.

[0188] As an example, the dwell time is obtained by the core network based on the ID of the federated learning server, a time ID used to characterize time, and the density of federated learning clients within the coverage area of ​​the federated learning server.

[0189] As an example, the dwell time is obtained by the core network based on the moving speed of the federated learning client.

[0190] For the description of model / computation offloading, please refer to the description of the calculation offloading analysis function in the electronic device 2000 embodiment above, which will not be repeated here.

[0191] In the process of describing the electronic device 2000 and the electronic device 9000 in the above embodiments, it is obvious that some processes or methods are also disclosed. Below, an overview of these methods is given without repeating some of the details already discussed above, but it should be noted that although these methods are disclosed in the process of describing the above electronic devices, these methods do not necessarily use the components described or are not necessarily performed by those components. For example, the embodiments of the above electronic devices can be partially or completely implemented using hardware and / or firmware, while the methods discussed below can be completely implemented by computer-executable programs, although these methods can also use the hardware and / or firmware of the electronic device.

[0192] FIG10 shows a flowchart of a method S1000 for a federated learning server according to an embodiment of the present disclosure. Method S1000 begins at step S1002. In step S1004, information about the magnitude of the parameters of the global model used for federated learning is sent to the core network to assist the core network in identifying, from among multiple federated learning clients, federated learning clients that are unable to upload all the parameters of their local models as partial uploading clients. In step S1006, if predetermined conditions are met, aggregation is performed based on the partial parameters of the local models received from the partial uploading clients to obtain a global model in the current round of training for federated learning. Method S1000 ends at step S1008.

[0193] The method may be executed, for example, by the electronic device 2000 described above. For specific details, please refer to the description of the related processing of the electronic device 2000, which will not be repeated here.

[0194] FIG11 illustrates a flowchart of a method S1100 for a core network according to another embodiment of the present disclosure. Method S1100 begins at step S1102. At step S1104, information regarding the magnitude of parameters of a global model used for federated learning is received from a federated learning server. This information is used to identify, from among multiple federated learning clients, federated learning clients that are unable to upload all parameters of their local models as partial uploading clients. This allows the federated learning server to aggregate the partial parameters of the local models received from the partial uploading clients, if predetermined conditions are met, to obtain a global model for the current round of federated learning training. Method S1100 concludes at step S1106.

[0195] The method may be executed, for example, by the electronic device 8000 described above. For specific details, please refer to the description of the related processing of the electronic device 8000, which will not be repeated here.

[0196] FIG12 shows a flowchart of a method S1200 for a federated learning client according to another embodiment of the present disclosure. Method S1200 begins at step S1202. In step S1204, if a predetermined condition is met, partial parameters of a local model for federated learning are sent to a federated learning server, so that the federated learning server can aggregate the local model based on the partial parameters to obtain a global model in the current round of federated learning training. The federated learning server sends magnitude information about the magnitude of the parameters of the global model to the core network to assist the core network in identifying the federated learning client as a partial upload client that is unable to upload all the parameters of its local model. Method S1200 ends at step S1206.

[0197] The method can be executed, for example, by the electronic device 9000 described above. For specific details, please refer to the description of the relevant processing of the electronic device 9000, which will not be repeated here.

[0198] The technology of the present disclosure can be applied to various products.

[0199] The electronic device 2000 can be set on the base station side or connected to the base station. The base station can be implemented as any type of evolved Node B (eNB) or gNB (5G base station). eNB includes, for example, macro eNB and small eNB. Small eNB can be an eNB that covers a cell smaller than a macro cell, such as a pico eNB, micro eNB, and home (femto) eNB. Similar situations can also be encountered for gNB. Alternatively, the base station can be implemented as any other type of base station, such as a NodeB and a base transceiver station (BTS). The base station may include: a main body (also called a base station device) configured to control wireless communications; and one or more remote radio heads (RRHs) arranged in a place different from the main body. In addition, various types of electronic devices can work as a base station by temporarily or semi-permanently performing base station functions.

[0200] The electronic device 9000 can be implemented as various user devices. The user device can be implemented as a mobile terminal (such as a smartphone, a tablet personal computer (PC), a notebook PC, a portable game terminal, a portable / dongle-type mobile router, and a digital camera) or an in-vehicle terminal (such as a car navigation device). The user device can also be implemented as a terminal that performs machine-to-machine (M2M) communication (also known as a machine type communication (MTC) terminal). In addition, the user device can be a wireless communication module (such as an integrated circuit module including a single chip) installed on each of the above terminals.

[0201] [Application examples for base stations]

[0202] (First application example)

[0203] FIG13 is a block diagram illustrating a first example of a schematic configuration of an eNB or gNB to which the techniques of this disclosure can be applied. Note that the following description uses an eNB as an example, but is equally applicable to a gNB. An eNB 800 includes one or more antennas 810 and a base station device 820. The base station device 820 and each antenna 810 can be connected to each other via an RF cable.

[0204] Each of the antennas 810 includes a single or multiple antenna elements (such as multiple antenna elements included in a multiple-input multiple-output (MIMO) antenna) and is used for base station device 820 to transmit and receive wireless signals. As shown in FIG13 , eNB 800 may include multiple antennas 810. For example, multiple antennas 810 may be compatible with multiple frequency bands used by eNB 800. Although FIG13 shows an example in which eNB 800 includes multiple antennas 810, eNB 800 may also include a single antenna 810.

[0205] The base station device 820 includes a controller 821 , a memory 822 , a network interface 823 , and a wireless communication interface 825 .

[0206] The controller 821 may be, for example, a CPU or a DSP, and operates various functions of the higher layers of the base station device 820. For example, the controller 821 generates data packets based on the data in the signal processed by the wireless communication interface 825, and transmits the generated packets via the network interface 823. The controller 821 may bundle data from multiple baseband processors to generate bundled packets, and transmit the generated bundled packets. The controller 821 may have logic functions for performing the following controls: the control may be radio resource control, radio bearer control, mobility management, admission control, and scheduling. The control may be performed in conjunction with a nearby eNB or core network node. The memory 822 includes RAM and ROM, and stores programs executed by the controller 821 and various types of control data (such as a terminal list, transmission power data, and scheduling data).

[0207] The network interface 823 is a communication interface for connecting the base station device 820 to the core network 824. The controller 821 can communicate with the core network node or another eNB via the network interface 823. In this case, the eNB 800 and the core network node or other eNBs can be connected to each other through a logical interface (such as an S1 interface and an X2 interface). The network interface 823 can also be a wired communication interface or a wireless communication interface for a wireless backhaul line. If the network interface 823 is a wireless communication interface, the network interface 823 can use a higher frequency band for wireless communication than the frequency band used by the wireless communication interface 825.

[0208] The wireless communication interface 825 supports any cellular communication scheme, such as Long Term Evolution (LTE) and LTE-Advanced, and provides wireless connectivity to terminals located in the cell of the eNB 800 via the antenna 810. The wireless communication interface 825 may typically include, for example, a baseband (BB) processor 826 and RF circuitry 827. The BB processor 826 can perform various signal processing functions, such as encoding / decoding, modulation / demodulation, and multiplexing / demultiplexing, and performs various types of signal processing for layers such as Layer 1, Medium Access Control (MAC), Radio Link Control (RLC), and Packet Data Convergence Protocol (PDCP). In place of the controller 821, the BB processor 826 may have some or all of the aforementioned logical functions. The BB processor 826 may be a memory that stores communication control programs, or a module including a processor configured to execute programs and associated circuitry. Program updates can modify the functionality of the BB processor 826. This module may be a card or blade inserted into a slot in the base station device 820. Alternatively, the module may be a chip mounted on the card or blade. Meanwhile, the RF circuit 827 may include, for example, a mixer, a filter, and an amplifier, and transmit and receive wireless signals via the antenna 810 .

[0209] As shown in FIG13 , the wireless communication interface 825 may include multiple BB processors 826. For example, multiple BB processors 826 may be compatible with multiple frequency bands used by the eNB 800. As shown in FIG13 , the wireless communication interface 825 may include multiple RF circuits 827. For example, multiple RF circuits 827 may be compatible with multiple antenna elements. Although FIG13 illustrates an example in which the wireless communication interface 825 includes multiple BB processors 826 and multiple RF circuits 827, the wireless communication interface 825 may also include a single BB processor 826 or a single RF circuit 827.

[0210] When the electronic device 2000 is implemented as the eNB 800 shown in FIG13 , its transceiver may be implemented by the wireless communication interface 825. At least a portion of the functionality may also be implemented by the controller 821. For example, the controller 821 may reduce the communication overhead of FL model training by executing the functions of the units in the electronic device 2000 without affecting the global model accuracy.

[0211] (Second application example)

[0212] FIG14 is a block diagram illustrating a second example of a schematic configuration of an eNB or gNB to which the techniques of this disclosure can be applied. Note that similarly, the following description uses an eNB as an example, but is equally applicable to a gNB. An eNB 830 includes one or more antennas 840, a base station device 850, and an RRH 860. The RRH 860 and each antenna 840 can be connected to each other via an RF cable. The base station device 850 and the RRH 860 can be connected to each other via a high-speed line such as an optical fiber cable.

[0213] Each of the antennas 840 includes a single or multiple antenna elements (such as multiple antenna elements included in a MIMO antenna) and is used for RRH 860 to transmit and receive wireless signals. As shown in FIG14 , eNB 830 may include multiple antennas 840. For example, multiple antennas 840 may be compatible with multiple frequency bands used by eNB 830. Although FIG14 shows an example in which eNB 830 includes multiple antennas 840, eNB 830 may also include a single antenna 840.

[0214] Base station device 850 includes a controller 851, memory 852, network interface 853, wireless communication interface 855, and connection interface 857. Controller 851, memory 852, and network interface 853 are the same as controller 821, memory 822, and network interface 823 described with reference to FIG.

[0215] The wireless communication interface 855 supports any cellular communication scheme (such as LTE and LTE-Advanced) and provides wireless communication to terminals located in the sector corresponding to the RRH 860 via the RRH 860 and the antenna 840. The wireless communication interface 855 may generally include, for example, a BB processor 856. The BB processor 856 is the same as the BB processor 826 described with reference to FIG. 14, except that the BB processor 856 is connected to the RF circuit 864 of the RRH 860 via the connection interface 857. As shown in FIG. 14, the wireless communication interface 855 may include multiple BB processors 856. For example, the multiple BB processors 856 may be compatible with multiple frequency bands used by the eNB 830. Although FIG. 14 shows an example in which the wireless communication interface 855 includes multiple BB processors 856, the wireless communication interface 855 may also include a single BB processor 856.

[0216] The connection interface 857 is an interface for connecting the base station device 850 (wireless communication interface 855) to the RRH 860. The connection interface 857 may also be a communication module for connecting the base station device 850 (wireless communication interface 855) to the RRH 860 for communication in the high-speed line.

[0217] The RRH 860 includes a connection interface 861 and a wireless communication interface 863 .

[0218] The connection interface 861 is an interface for connecting the RRH 860 (wireless communication interface 863) to the base station device 850. The connection interface 861 may also be a communication module for communication in the above-mentioned high-speed line.

[0219] The wireless communication interface 863 transmits and receives wireless signals via the antenna 840. The wireless communication interface 863 may generally include, for example, an RF circuit 864. The RF circuit 864 may include, for example, a mixer, a filter, and an amplifier, and transmits and receives wireless signals via the antenna 840. As shown in FIG14 , the wireless communication interface 863 may include multiple RF circuits 864. For example, the multiple RF circuits 864 may support multiple antenna elements. Although FIG14 shows an example in which the wireless communication interface 863 includes multiple RF circuits 864, the wireless communication interface 863 may also include a single RF circuit 864.

[0220] When the electronic device 2000 is implemented as the eNB 830 shown in FIG14 , its transceiver may be implemented by the wireless communication interface 855. At least a portion of the functionality may also be implemented by the controller 851. For example, the controller 851 may reduce the communication overhead of FL model training by executing the functions of the units in the electronic device 2000 without affecting the global model accuracy.

[0221] [Application examples on user devices]

[0222] (First application example)

[0223] 15 is a block diagram showing an example of a schematic configuration of a smartphone 900 to which the technology of the present disclosure can be applied. The smartphone 900 includes a processor 901, a memory 902, a storage device 903, an external connection interface 904, a camera 906, a sensor 907, a microphone 908, an input device 909, a display device 910, a speaker 911, a wireless communication interface 912, one or more antenna switches 915, one or more antennas 916, a bus 917, a battery 918, and an auxiliary controller 919.

[0224] The processor 901 may be, for example, a CPU or a system on a chip (SoC), and controls the functions of the application layer and other layers of the smartphone 900. The memory 902 includes RAM and ROM, and stores data and programs executed by the processor 901. The storage device 903 may include storage media such as semiconductor memories and hard disks. The external connection interface 904 is an interface for connecting external devices (such as memory cards and universal serial bus (USB) devices) to the smartphone 900.

[0225] The camera 906 includes an image sensor such as a charge coupled device (CCD) and a complementary metal oxide semiconductor (CMOS) and generates a captured image. The sensor 907 may include a group of sensors such as a measurement sensor, a gyroscope sensor, a geomagnetic sensor, and an acceleration sensor. The microphone 908 converts the sound input to the smartphone 900 into an audio signal. The input device 909 includes, for example, a touch sensor, a keypad, a keyboard, a button, or a switch configured to detect a touch on the screen of the display device 910, and receives an operation or information input from the user. The display device 910 includes a screen such as a liquid crystal display (LCD) and an organic light emitting diode (OLED) display and displays an output image of the smartphone 900. The speaker 911 converts the audio signal output from the smartphone 900 into sound.

[0226] The wireless communication interface 912 supports any cellular communication scheme (such as LTE and LTE-Advanced) and performs wireless communications. The wireless communication interface 912 may typically include, for example, a BB processor 913 and an RF circuit 914. The BB processor 913 may perform, for example, encoding / decoding, modulation / demodulation, and multiplexing / demultiplexing, and may also perform various types of signal processing for wireless communications. Meanwhile, the RF circuit 914 may include, for example, mixers, filters, and amplifiers, and transmit and receive wireless signals via an antenna 916. Note that while the figure shows a scenario where one RF link is connected to one antenna, this is merely illustrative, and also encompasses scenarios where one RF link is connected to multiple antennas via multiple phase shifters. The wireless communication interface 912 may be a chip module on which the BB processor 913 and RF circuit 914 are integrated. As shown in FIG15 , the wireless communication interface 912 may include multiple BB processors 913 and multiple RF circuits 914. While FIG15 illustrates an example in which the wireless communication interface 912 includes multiple BB processors 913 and multiple RF circuits 914, the wireless communication interface 912 may also include a single BB processor 913 or a single RF circuit 914.

[0227] In addition, in addition to the cellular communication scheme, the wireless communication interface 912 can support other types of wireless communication schemes, such as a short-range wireless communication scheme, a near-field communication scheme, and a wireless local area network (LAN) scheme. In this case, the wireless communication interface 912 may include a BB processor 913 and an RF circuit 914 for each wireless communication scheme.

[0228] Each of the antenna switches 915 switches a connection destination of the antenna 916 between a plurality of circuits (eg, circuits for different wireless communication schemes) included in the wireless communication interface 912 .

[0229] Each of the antennas 916 includes a single or multiple antenna elements (such as multiple antenna elements included in a MIMO antenna) and is used for transmitting and receiving wireless signals via the wireless communication interface 912. As shown in FIG15 , the smartphone 900 may include multiple antennas 916. Although FIG15 shows an example in which the smartphone 900 includes multiple antennas 916, the smartphone 900 may also include a single antenna 916.

[0230] In addition, the smartphone 900 may include an antenna 916 for each wireless communication scheme. In this case, the antenna switch 915 may be omitted from the configuration of the smartphone 900.

[0231] The bus 917 connects the processor 901, the memory 902, the storage device 903, the external connection interface 904, the camera 906, the sensor 907, the microphone 908, the input device 909, the display device 910, the speaker 911, the wireless communication interface 912, and the auxiliary controller 919. The battery 918 supplies power to the various blocks of the smartphone 900 shown in FIG15 via feeders, which are partially shown as dotted lines in the figure. The auxiliary controller 919 operates the minimum necessary functions of the smartphone 900, for example, in sleep mode.

[0232] When the electronic device 9000 is implemented as a smartphone as a user device, such as the smartphone 900 shown in FIG15 , the transceiver of the electronic device 9000 may be implemented by the wireless communication interface 912. At least a portion of the functionality may also be implemented by the processor 901 or the auxiliary controller 919. For example, by executing the functions of the units in the electronic device 9000, the processor 901 or the auxiliary controller 919 can reduce the communication overhead of FL model training without affecting the global model accuracy.

[0233] (Second application example)

[0234] 16 is a block diagram showing an example of a schematic configuration of a car navigation device 920 to which the technology of the present disclosure can be applied. The car navigation device 920 includes a processor 921, a memory 922, a global positioning system (GPS) module 924, a sensor 925, a data interface 926, a content player 927, a storage medium interface 928, an input device 929, a display device 930, a speaker 931, a wireless communication interface 933, one or more antenna switches 936, one or more antennas 937, and a battery 938.

[0235] The processor 921 may be, for example, a CPU or an SoC, and controls a navigation function and other functions of the car navigation apparatus 920. The memory 922 includes a RAM and a ROM, and stores data and programs executed by the processor 921.

[0236] The GPS module 924 measures the position (such as latitude, longitude, and altitude) of the car navigation device 920 using GPS signals received from GPS satellites. The sensor 925 may include a group of sensors such as a gyroscope sensor, a geomagnetic sensor, and an air pressure sensor. The data interface 926 is connected to, for example, the in-vehicle network 941 via an unillustrated terminal and acquires data generated by the vehicle (such as vehicle speed data).

[0237] The content player 927 reproduces content stored in a storage medium (such as a CD or DVD) inserted into the storage medium interface 928. The input device 929 includes, for example, a touch sensor, button, or switch configured to detect a touch on the screen of the display device 930, and receives an operation or information input from the user. The display device 930 includes a screen such as an LCD or OLED display and displays an image of a navigation function or reproduced content. The speaker 931 outputs the sound of the navigation function or the reproduced content.

[0238] The wireless communication interface 933 supports any cellular communication scheme (such as LTE and LTE-Advanced) and performs wireless communication. The wireless communication interface 933 may generally include, for example, a BB processor 934 and an RF circuit 935. The BB processor 934 may perform, for example, encoding / decoding, modulation / demodulation, and multiplexing / demultiplexing, and perform various types of signal processing for wireless communication. Meanwhile, the RF circuit 935 may include, for example, a mixer, a filter, and an amplifier, and transmit and receive wireless signals via an antenna 937. The wireless communication interface 933 may also be a chip module on which the BB processor 934 and the RF circuit 935 are integrated. As shown in Figure 16, the wireless communication interface 933 may include multiple BB processors 934 and multiple RF circuits 935. Although Figure 16 shows an example in which the wireless communication interface 933 includes multiple BB processors 934 and multiple RF circuits 935, the wireless communication interface 933 may also include a single BB processor 934 or a single RF circuit 935.

[0239] In addition, in addition to the cellular communication scheme, the wireless communication interface 933 can support other types of wireless communication schemes, such as a short-range wireless communication scheme, a near field communication scheme, and a wireless LAN scheme. In this case, for each wireless communication scheme, the wireless communication interface 933 can include a BB processor 934 and an RF circuit 935.

[0240] Each of the antenna switches 936 switches a connection destination of the antenna 937 between a plurality of circuits included in the wireless communication interface 933 , such as circuits for different wireless communication schemes.

[0241] Each of the antennas 937 includes a single or multiple antenna elements (such as multiple antenna elements included in a MIMO antenna) and is used for transmitting and receiving wireless signals via the wireless communication interface 933. As shown in FIG16, the car navigation device 920 may include multiple antennas 937. Although FIG16 shows an example in which the car navigation device 920 includes multiple antennas 937, the car navigation device 920 may also include a single antenna 937.

[0242] Furthermore, the car navigation device 920 may include an antenna 937 for each wireless communication scheme. In this case, the antenna switch 936 may be omitted from the configuration of the car navigation device 920.

[0243] The battery 938 supplies power to the respective blocks of the car navigation apparatus 920 shown in Fig. 16 via a feeder line, which is partially shown as a dotted line in the figure. The battery 938 accumulates the power supplied from the vehicle.

[0244] When the electronic device 9000 is implemented as a car navigation device on the user device side, such as the car navigation device 920 shown in FIG. 16 , the transceiver of the electronic device 9000 may be implemented by the wireless communication interface 933. At least a portion of the functionality may also be implemented by the processor 921. For example, by executing the functions of the units in the electronic device 9000, the processor 921 can reduce the communication overhead of FL model training without affecting the global model accuracy.

[0245] The technology of the present disclosure can also be implemented as an in-vehicle system (or vehicle) 940 including a car navigation device 920, an in-vehicle network 941, and one or more blocks of a vehicle module 942. The vehicle module 942 generates vehicle data (such as vehicle speed, engine speed, and fault information) and outputs the generated data to the in-vehicle network 941.

[0246] The basic principles of the present invention are described above in conjunction with specific embodiments. However, it should be pointed out that those skilled in the art will understand that all or any steps or components of the methods and devices of the present invention can be implemented in any computing device (including a processor, storage medium, etc.) or a network of computing devices in the form of hardware, firmware, software, or a combination thereof. This can be achieved by those skilled in the art using their basic circuit design knowledge or basic programming skills after reading the description of the present invention.

[0247] Furthermore, the present invention also provides a program product storing machine-readable instruction codes. When the instruction codes are read and executed by a machine, the method according to the embodiment of the present invention can be executed.

[0248] Accordingly, the storage medium for carrying the program product storing the machine-readable instruction code is also included in the disclosure of the present invention. The storage medium includes but is not limited to a floppy disk, an optical disk, a magneto-optical disk, a memory card, a memory stick, and the like.

[0249] When the present invention is implemented through software or firmware, the programs constituting the software are installed from a storage medium or a network to a computer with a dedicated hardware structure (such as the general-purpose computer 1700 shown in Figure 17). When various programs are installed on the computer, it can perform various functions, etc.

[0250] 17 , a central processing unit (CPU) 1701 executes various processes according to a program stored in a read-only memory (ROM) 1702 or a program loaded from a storage section 1708 to a random access memory (RAM) 1703. In the RAM 1703, data required when the CPU 1701 executes various processes, etc., is also stored as needed. The CPU 1701, the ROM 1702, and the RAM 1703 are connected to each other via a bus 1704. An input / output interface 1705 is also connected to the bus 1704.

[0251] The following components are connected to the input / output interface 1705: an input section 1706 (including a keyboard, a mouse, etc.), an output section 1707 (including a display such as a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and speakers, etc.), a storage section 1708 (including a hard disk, etc.), and a communication section 1709 (including a network interface card such as a LAN card, a modem, etc.). The communication section 1709 performs communication processing via a network such as the Internet. A drive 1710 may also be connected to the input / output interface 1705 as needed. A removable medium 1711 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc. is installed in the drive 1710 as needed, so that a computer program read therefrom is installed in the storage section 1708 as needed.

[0252] In the case of realizing the above-described series of processing by software, a program constituting the software is installed from a network such as the Internet or a storage medium such as the removable medium 1711 .

[0253] It should be understood by those skilled in the art that such storage media is not limited to the removable medium 1711 shown in FIG. 17 , which stores the program therein and is distributed separately from the device to provide the program to the user. Examples of the removable medium 1711 include magnetic disks (including floppy disks (registered trademark)), optical disks (including compact disk read-only memories (CD-ROMs) and digital versatile disks (DVDs)), magneto-optical disks (including minidiscs (MDs) (registered trademark)), and semiconductor memories. Alternatively, the storage medium may be the ROM 1702, a hard disk included in the storage section 1708, or the like, in which the program is stored and distributed to the user together with the device containing them.

[0254] It should also be noted that in the apparatus, method, and system of the present invention, each component or step can be decomposed and / or recombined. Such decomposition and / or recombination should be considered equivalent solutions of the present invention. Furthermore, the steps of performing the above series of processes can naturally be performed in chronological order according to the order described, but do not necessarily need to be performed in chronological order. Certain steps can be performed in parallel or independently of each other.

[0255] Finally, it should be noted that the terms "comprises," "comprising," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. Furthermore, in the absence of further limitations, an element defined by the phrase "comprising a ..." does not preclude the presence of additional identical elements in the process, method, article, or apparatus that includes the element.

[0256] Although the embodiments of the present invention have been described in detail above with reference to the accompanying drawings, it should be understood that the embodiments described above are merely illustrative of the present invention and are not intended to limit the present invention. It will be apparent to those skilled in the art that various modifications and variations may be made to the embodiments described above without departing from the spirit and scope of the present invention. Therefore, the scope of the present invention is limited solely by the appended claims and their equivalents.

[0257] The present technology can also be implemented as follows.

[0258] Solution 1. An electronic device for a federated learning server, comprising:

[0259] at least one processor; and

[0260] at least one memory including computer program code, wherein the at least one memory and the computer program code are configured to, through the at least one processor, cause the electronic device to execute:

[0261] Sending magnitude information about the magnitude of parameters of the global model used for federated learning to the core network to assist the core network in identifying a federated learning client that cannot upload all parameters of its local model from among multiple federated learning clients as a partial uploading client, and

[0262] When predetermined conditions are met, aggregation is performed based on partial parameters of the local model received from the partial upload client to obtain a global model in a current round of training of federated learning.

[0263] Solution 2. The electronic device according to Solution 1, wherein the magnitude information includes information about the size of the parameters of the global model.

[0264] Solution 3. The electronic device according to Solution 1 or 2, wherein:

[0265] The predetermined conditions include receiving a list of the partial uploading clients from the core network and / or the accuracy of the global model in the last round of training reaches a preset accuracy, wherein the list includes the IDs of the partial uploading clients, and

[0266] When the accuracy of the global model in the previous round of training reaches the preset accuracy, the multiple federated learning clients all serve as the partial uploading clients.

[0267] Solution 4. The electronic device according to Solution 3, wherein:

[0268] The IDs of some uploading clients included in the list are determined by the core network based on the magnitude information and the predicted channel information between the electronic device and the federated learning client.

[0269] Solution 5. The electronic device according to Solution 4, wherein:

[0270] The channel information includes at least one of a channel quality indicator CQI, a precoding matrix indicator PMI, a reference signal received power RSRP, and a signal-to-noise ratio SNR of a channel between the electronic device and the federated learning client.

[0271] Solution 6. The electronic device according to any one of Solutions 1 to 5, wherein the at least one memory and the computer program code are configured to, through the at least one processor, cause the electronic device to execute:

[0272] For the parameters of the global model in the previous round of training and the parameters of the local models uploaded by the multiple federated learning clients in the previous round of training:

[0273] Calculating a local model parameter deviation degree indicating a degree of dispersion between parameters of the local models of the plurality of federated learning clients, and calculating a global model parameter deviation degree indicating a degree of deviation between parameters of the local models of the plurality of federated learning clients and parameters of the global model, and

[0274] The partial parameters are determined based on the local model parameter deviation degree and the global model parameter deviation degree.

[0275] Solution 7. The electronic device according to Solution 6, wherein the at least one memory and the computer program code are configured to, through the at least one processor, cause the electronic device to execute:

[0276] Calculating an average value of the i-th parameter based on the i-th parameters of the local models of the multiple federated learning clients, and calculating a degree of local model parameter deviation for the i-th parameter based on a difference between the i-th parameter of the local model of each federated learning client and the average value; and

[0277] Based on the difference between the i-th parameter of the local model of each federated learning client and the i-th parameter of the global model, the degree of global model parameter deviation for the i-th parameter is calculated.

[0278] Solution 8. The electronic device according to Solution 6 or 7, wherein the at least one memory and the computer program code are configured to, through the at least one processor, cause the electronic device to execute:

[0279] Based on the degree of deviation of the local model parameters and the degree of deviation of the global model parameters, clustering the parameters is performed using a clustering method to obtain multiple clusters.

[0280] Selecting a selected cluster that meets a predetermined cluster condition from among the plurality of clusters, and

[0281] The parameters in the selected cluster are used as the partial parameters.

[0282] Solution 9. The electronic device according to Solution 8, wherein:

[0283] The predetermined cluster condition includes that the probability of being selected corresponding to the cluster is greater than the predetermined probability, and

[0284] The at least one memory and the computer program code are configured to, through the at least one processor, cause the electronic device to execute:

[0285] The local model parameter deviation degree and the global model parameter deviation degree are respectively used as coordinates of a two-dimensional coordinate system, and the local model parameter deviation degree and the global model parameter deviation degree corresponding to the calculated parameter are used as coordinate values, so that each parameter is represented as a point in the coordinate system,

[0286] Clustering all points in the coordinate system using the K-Means algorithm to obtain the multiple clusters, and

[0287] For each cluster in at least a portion of the plurality of clusters, a probability of the cluster being selected is calculated based on a distance between the cluster center and the coordinate origin, and an angle between a line connecting the cluster center to the coordinate origin and a dividing line of the first quadrant of the coordinate system, wherein the dividing line is a straight line passing through the coordinate origin and forming a predetermined angle with the horizontal axis of the first quadrant.

[0288] Among them, as the distance increases, the probability of being selected increases, and as the angle decreases, the probability of being selected increases.

[0289] Solution 10. The electronic device according to any one of Solutions 1 to 9, wherein the at least one memory and the computer program code are configured to, through the at least one processor, cause the electronic device to execute:

[0290] Notification information about the partial parameters is sent to the partial uploading client, so that the partial uploading client uploads only the partial parameters in the current round of training.

[0291] Solution 11. The electronic device according to Solution 10, wherein:

[0292] The global model is a layered neural network model,

[0293] The notification information includes position information of the partial parameters in the neural network model.

[0294] Solution 12. The electronic device according to Solution 11, wherein the at least one memory and the computer program code are configured to, through the at least one processor, cause the electronic device to execute:

[0295] Based on the location information, partial parameters of the local model received from the partial uploading client and all parameters of the local model received from other clients among the multiple federated learning clients are aligned, and the local models are aggregated.

[0296] Solution 13. An electronic device according to any one of Solutions 1 to 12, wherein the magnitude information is used as input to UE communication analysis in a network data analysis function NWDAF, and the UE communication prediction output of the UE communication analysis includes a list of IDs of the partial uploading clients.

[0297] Solution 14. The electronic device according to any one of Solutions 1 to 13, wherein the at least one memory and the computer program code are configured to, through the at least one processor, cause the electronic device to execute:

[0298] receiving a computation offloading instruction from the core network, indicating that the federated learning client is to perform computation offloading, and

[0299] Notify all federated learning clients within the coverage of the electronic device of the computation offloading indication, so that the federated learning clients can determine whether to perform computation offloading.

[0300] The computation offloading indication is sent by the core network based on the residence time of all federated learning clients within the coverage of the electronic device.

[0301] Solution 15. The electronic device according to Solution 14, wherein:

[0302] The computation offloading indication is sent by the core network when it is determined that the dwell time is less than the training duration of the preset local model.

[0303] Solution 16. The electronic device according to Solution 14 or 15, wherein:

[0304] The dwell time is obtained by the core network based on the ID of the electronic device, a time ID used to represent time, and a density of federated learning clients within the coverage of the electronic device.

[0305] Solution 17. The electronic device according to Solution 16, wherein:

[0306] The residence time is obtained by the core network based on the moving speed of the federated learning client.

[0307] Solution 18. An electronic device for a core network, comprising:

[0308] at least one processor; and

[0309] at least one memory including computer program code, wherein the at least one memory and the computer program code are configured to, through the at least one processor, cause the electronic device to execute:

[0310] Receive magnitude information about parameter magnitudes of a global model used for federated learning from a federated learning server to identify a federated learning client that cannot upload all parameters of its local model from a plurality of federated learning clients as a partial uploading client, so that when predetermined conditions are met, the federated learning server aggregates the partial parameters of the local model received from the partial uploading client to obtain a global model in a current round of training of the federated learning.

[0311] Solution 19. The electronic device according to Solution 18, wherein the magnitude information includes information about the size of the parameters of the global model.

[0312] Solution 20. The electronic device according to Solution 18 or 19, wherein:

[0313] The predetermined conditions include that the federated learning server receives a list of the partial uploading clients from the electronic device and / or the accuracy of the global model in the previous round of training reaches a preset accuracy, wherein the list includes the IDs of the partial uploading clients.

[0314] Solution 21. The electronic device according to Solution 20, wherein the at least one memory and the computer program code are configured to, through the at least one processor, cause the electronic device to execute:

[0315] The IDs of some uploading clients included in the list are determined based on the magnitude information and the predicted channel information between the federated learning server and the federated learning client.

[0316] Solution 22. The electronic device according to Solution 21, wherein:

[0317] The channel information includes at least one of a channel quality indicator CQI, a precoding matrix indicator PMI, a reference signal received power RSRP, and a signal-to-noise ratio SNR of the channel between the federated learning server and the federated learning client.

[0318] Solution 23. An electronic device according to any one of Solutions 18 to 22, wherein the magnitude information is used as input to a UE communication analysis in a network data analysis function NWDAF, and the UE communication prediction output of the UE communication analysis includes a list of IDs of the partial uploading clients.

[0319] Solution 24. The electronic device according to any one of Solution 18 to Solution 23, wherein the at least one memory and the computer program code are configured to, through the at least one processor, cause the electronic device to execute:

[0320] Based on the residence time of all federated learning clients within the coverage of the federated learning server, a computation offloading indication is sent to the federated learning server, instructing the federated learning client to perform computation offloading, so that the federated learning server notifies all federated learning clients within its coverage of the computation offloading indication, so that the federated learning client can determine whether to perform computation offloading.

[0321] Solution 25. The electronic device according to Solution 24, wherein the at least one memory and the computer program code are configured to, through the at least one processor, cause the electronic device to execute:

[0322] When it is determined that the dwell time is less than the preset training duration of the local model, the calculation offloading indication is sent.

[0323] Solution 26. The electronic device according to Solution 24 or 25, wherein the at least one memory and the computer program code are configured to, through the at least one processor, cause the electronic device to execute:

[0324] The residence time is obtained based on the ID of the federated learning server, a time ID used to represent time, and a density of federated learning clients within the coverage area of ​​the federated learning server.

[0325] Solution 27. The electronic device according to Solution 26, wherein the at least one memory and the computer program code are configured to, through the at least one processor, cause the electronic device to execute:

[0326] The dwell time is also obtained based on the moving speed of the federated learning client.

[0327] Solution 28. An electronic device for a federated learning client, comprising:

[0328] at least one processor; and

[0329] at least one memory including computer program code, wherein the at least one memory and the computer program code are configured to, through the at least one processor, cause the electronic device to execute:

[0330] When predetermined conditions are met, partial parameters of the local model for federated learning are sent to the federated learning server, so that the federated learning server aggregates the local model based on the partial parameters to obtain the global model in the current round of federated learning training.

[0331] The federated learning server sends magnitude information about the magnitude of parameters of the global model to the core network to assist the core network in identifying the electronic device as a partial upload client that cannot upload all parameters of its local model.

[0332] Option 29. An electronic device according to Option 28, wherein the magnitude information includes information about the size of the parameters of the global model.

[0333] Solution 30. The electronic device according to Solution 28 or 29, wherein:

[0334] The predetermined conditions include that the federated learning server receives a list including the IDs of the partial uploading clients from the core network and / or the accuracy of the global model in the previous round of training reaches a preset accuracy.

[0335] Solution 31. The electronic device according to any one of Solution 28 to Solution 30, wherein the at least one memory and the computer program code are configured to, through the at least one processor, cause the electronic device to execute:

[0336] Notification information about the partial parameters is received from the federated learning server.

[0337] Solution 32. The electronic device according to Solution 31, wherein:

[0338] The global model is a layered neural network model,

[0339] The notification information includes position information of the partial parameters in the neural network model.

[0340] Solution 33. An electronic device according to any one of Solutions 28 to 32, wherein the magnitude information is used as input to a UE communication analysis in a network data analysis function NWDAF, and the UE communication prediction output of the UE communication analysis includes a list of IDs of some uploading clients.

[0341] Solution 34. The electronic device according to any one of Solution 28 to Solution 33, wherein the at least one memory and the computer program code are configured to, through the at least one processor, cause the electronic device to execute:

[0342] receiving a computation offloading instruction from the federated learning server, indicating that the federated learning client is to perform computation offloading, so as to determine whether to perform the computation offloading;

[0343] The computation offloading indication is sent by the core network to the federated learning server based on the residence time of all federated learning clients within the coverage of the federated learning server.

[0344] Solution 35. The electronic device according to Solution 34, wherein:

[0345] The computation offloading indication is sent by the core network when it is determined that the dwell time is less than the training duration of the preset local model.

[0346] Solution 36. The electronic device according to Solution 34 or 35, wherein:

[0347] The residence time is obtained by the core network based on the ID of the federated learning server, a time ID used to represent time, and a density of federated learning clients within the coverage area of ​​the federated learning server.

[0348] Solution 37. The electronic device according to Solution 36, wherein:

[0349] The residence time is obtained by the core network based on the moving speed of the federated learning client.

[0350] Solution 38. A method for a federated learning server, comprising:

[0351] Sending magnitude information about the magnitude of parameters of the global model used for federated learning to the core network to assist the core network in identifying a federated learning client that cannot upload all parameters of its local model from among multiple federated learning clients as a partial uploading client, and

[0352] When predetermined conditions are met, aggregation is performed based on partial parameters of the local model received from the partial upload client to obtain a global model in a current round of training of federated learning.

[0353] Solution 39. A method for a core network, comprising:

[0354] Receive magnitude information about parameter magnitudes of a global model used for federated learning from a federated learning server to identify a federated learning client that cannot upload all parameters of its local model from a plurality of federated learning clients as a partial uploading client, so that when predetermined conditions are met, the federated learning server aggregates the partial parameters of the local model received from the partial uploading client to obtain a global model in a current round of training of the federated learning.

[0355] Solution 40. A method for a federated learning client, comprising:

[0356] When predetermined conditions are met, partial parameters of the local model for federated learning are sent to the federated learning server, so that the federated learning server aggregates the local model based on the partial parameters to obtain the global model in the current round of federated learning training.

[0357] The federated learning server sends magnitude information about the parameter magnitudes of the global model to the core network to assist the core network in identifying the federated learning client as a partial upload client that cannot upload all parameters of its local model.

[0358] Option 41. A computer-readable storage medium having computer-executable instructions stored thereon, which, when executed, performs the method according to any one of Option 38 to Option 40.

Claims

1. An electronic device for a federated learning server, comprising: at least one processor; and at least one memory including computer program code, wherein the at least one memory and the computer program code are configured to, through the at least one processor, cause the electronic device to execute: sending magnitude information about the magnitude of parameters of the global model for federated learning to a core network to assist the core network in identifying a federated learning client that cannot upload all parameters of its local model from among a plurality of federated learning clients as a partial uploading client, and When predetermined conditions are met, aggregation is performed based on partial parameters of the local model received from the partial uploading client to obtain a global model in a current round of training of federated learning.

2. The electronic device according to claim 1, wherein: The magnitude information includes information about the magnitudes of parameters of the global model.

3. The electronic device according to claim 1 or 2, wherein: The predetermined condition includes receiving a list of the partial uploading clients from the core network and / or the accuracy of the global model in the previous round of training reaches a preset accuracy, wherein the list includes the IDs of the partial uploading clients, and When the accuracy of the global model in the previous round of training reaches the preset accuracy, the multiple federated learning clients all serve as the partial uploading clients.

4. The electronic device according to claim 3, wherein: The IDs of some uploading clients included in the list are determined by the core network based on the magnitude information and the predicted channel information between the electronic device and the federated learning client.

5. The electronic device according to claim 4, wherein: The channel information includes at least one of a channel quality indication CQI, a precoding matrix indication PMI, a reference signal received power RSRP, and a signal-to-noise ratio SNR of a channel between the electronic device and the federated learning client.

6. The electronic device according to any one of claims 1 to 5, wherein: The at least one memory and the computer program code are configured to, through the at least one processor, cause the electronic device to execute: For the parameters of the global model in the previous round of training and the parameters of the local models uploaded by the multiple federated learning clients in the previous round of training: Calculating a local model parameter deviation degree indicating a dispersion degree between parameters of the local models of the plurality of federated learning clients, and calculating a global model parameter deviation degree indicating a deviation degree between parameters of the local models of the plurality of federated learning clients and parameters of the global model, and The partial parameters are determined based on the local model parameter deviation degree and the global model parameter deviation degree.

7. The electronic device according to claim 6, wherein: The at least one memory and the computer program code are configured to, through the at least one processor, cause the electronic device to execute: Calculating an average value of the i-th parameter based on the i-th parameter of the local models of the multiple federated learning clients, and calculating a degree of local model parameter deviation for the i-th parameter based on a difference between the i-th parameter of the local model of each federated learning client and the average value; as well as Based on the difference between the i-th parameter of the local model of each federated learning client and the i-th parameter of the global model, the degree of global model parameter deviation for the i-th parameter is calculated.

8. The electronic device according to claim 6 or 7, wherein: The at least one memory and the computer program code are configured to, through the at least one processor, cause the electronic device to execute: Based on the local model parameter deviation degree and the global model parameter deviation degree, clustering the parameters using a clustering method to obtain a plurality of clusters after clustering. Selecting a selected cluster that satisfies a predetermined cluster condition from among the plurality of clusters, and The parameters in the selected cluster are used as the partial parameters.

9. The electronic device according to claim 8, wherein: The predetermined cluster condition includes that the probability of being selected corresponding to the cluster is greater than the predetermined probability, and The at least one memory and the computer program code are configured to A processor causes the electronic device to perform: The local model parameter deviation degree and the global model parameter deviation degree are respectively used as coordinates of a two-dimensional coordinate system, and the local model parameter deviation degree and the global model parameter deviation degree corresponding to the calculated parameter are used as coordinate values, so that each parameter is represented as a point in the coordinate system, Clustering all points in the coordinate system using a K-Means algorithm to obtain the plurality of clusters, and For each cluster in at least a portion of the plurality of clusters, the probability of the cluster being selected is calculated based on the distance between the cluster center and the coordinate origin, and the angle between a line from the cluster center to the coordinate origin and a dividing line of the first quadrant of the coordinate system, wherein the dividing line is a straight line passing through the coordinate origin and forming a predetermined angle with the horizontal axis of the first quadrant, Among them, as the distance increases, the probability of being selected increases, and as the angle decreases, the probability of being selected increases.

10. The electronic device according to any one of claims 1 to 9, wherein: The at least one memory and the computer program code are configured to, through the at least one processor, cause the electronic device to execute: Notification information about the partial parameters is sent to the partial uploading client, so that the partial uploading client only uploads the partial parameters in the current round of training.

11. The electronic device according to claim 10, wherein: The global model is a layered neural network model. The notification information includes location information of the partial parameters in the neural network model.

12. The electronic device according to claim 11, wherein: The at least one memory and the computer program code are configured to, through the at least one processor, cause the electronic device to execute: Based on the location information, partial parameters of the local model received from the partial uploading client and all parameters of the local model received from other clients among the multiple federated learning clients are aligned, and the local models are aggregated.

13. The electronic device according to any one of claims 1 to 12, wherein: The magnitude information is used as an input of UE communication analysis in a network data analysis function NWDAF, and a UE communication prediction output of the UE communication analysis includes a list having IDs of the partial uploading clients.

14. The electronic device according to any one of claims 1 to 13, wherein: The at least one memory and the computer program code are configured to, through the at least one processor, cause the electronic device to execute: receiving a computation offloading indication from the core network indicating that the federated learning client is to perform computation offloading, and Notify all federated learning clients within the coverage of the electronic device of the computation offloading indication, so that the federated learning clients can determine whether to perform computation offloading, The computation offloading indication is sent by the core network based on the residence time of all federated learning clients within the coverage of the electronic device.

15. The electronic device according to claim 14, wherein: The computation offloading indication is sent by the core network when it is determined that the residence time is less than the preset training duration of the local model.

16. The electronic device according to claim 14 or 15, wherein: The residence time is obtained by the core network based on the ID of the electronic device, a time ID used to characterize time, and a density of federated learning clients within the coverage of the electronic device.

17. The electronic device according to claim 16, wherein: The residence time is obtained by the core network based on the moving speed of the federated learning client.

18. An electronic device for a core network, comprising: at least one processor; and at least one memory including computer program code, wherein the at least one memory and the computer program code are configured to, through the at least one processor, cause the electronic device to execute: Receive information from the federated learning server about the parameter magnitudes of the global model used for federated learning The magnitude information is used to identify a federated learning client that cannot upload all the parameters of its local model from multiple federated learning clients as a partial uploading client, so that when a predetermined condition is met, the federated learning server aggregates the partial parameters of the local model received from the partial uploading client to obtain a global model in the current round of training of the federated learning.

19. The electronic device according to claim 18, wherein: The magnitude information includes information about the magnitudes of parameters of the global model.

20. The electronic device according to claim 18 or 19, wherein: The predetermined condition includes that the federated learning server receives a list of the partial uploading clients from the electronic device and / or the accuracy of the global model in the previous round of training reaches a preset accuracy, wherein the list includes the IDs of the partial uploading clients.

21. The electronic device according to claim 20, wherein: The at least one memory and the computer program code are configured to, through the at least one processor, cause the electronic device to execute: The IDs of some uploading clients included in the list are determined based on the magnitude information and the predicted channel information between the federated learning server and the federated learning client.

22. The electronic device according to claim 21, wherein: The channel information includes at least one of a channel quality indication CQI, a precoding matrix indication PMI, a reference signal received power RSRP, and a signal-to-noise ratio SNR of a channel between the federated learning server and the federated learning client.

23. The electronic device according to any one of claims 18 to 22, wherein: The magnitude information is used as an input of UE communication analysis in a network data analysis function NWDAF, and a UE communication prediction output of the UE communication analysis includes a list having IDs of the partial uploading clients.

24. The electronic device according to any one of claims 18 to 23, wherein: The at least one memory and the computer program code are configured to, through the at least one processor, cause the electronic device to execute: Based on the residence time of all federated learning clients within the coverage of the federated learning server, a computation offloading instruction is sent to the federated learning server to instruct the federated learning client to perform computation offloading, so that the federated learning server notifies all federated learning clients within its coverage of the computation offloading instruction, so that the federated learning client determines whether to perform computation offloading. Perform computation offloading.

25. The electronic device according to claim 24, wherein: The at least one memory and the computer program code are configured to, through the at least one processor, cause the electronic device to execute: When it is determined that the residence time is less than the preset training duration of the local model, the calculation offloading indication is sent.

26. The electronic device according to claim 24 or 25, wherein: The at least one memory and the computer program code are configured to, through the at least one processor, cause the electronic device to execute: The residence time is obtained based on the ID of the federated learning server, a time ID used to characterize time, and a density of federated learning clients within the coverage area of ​​the federated learning server.

27. The electronic device according to claim 26, wherein: The at least one memory and the computer program code are configured to, through the at least one processor, cause the electronic device to execute: The dwell time is also obtained based on a moving speed of the federated learning client.

28. An electronic device for a federated learning client, comprising: at least one processor; and at least one memory including computer program code, wherein the at least one memory and the computer program code are configured to, through the at least one processor, cause the electronic device to execute: When a predetermined condition is met, partial parameters of a local model for federated learning are sent to a federated learning server, so that the federated learning server aggregates the local model based on the partial parameters to obtain a global model in a current round of training of the federated learning. The federated learning server sends magnitude information about the magnitude of parameters of the global model to the core network to assist the core network in identifying the electronic device as a partial uploading client that cannot upload all parameters of its local model.

29. The electronic device according to claim 28, wherein: The magnitude information includes information about the magnitudes of parameters of the global model.

30. The electronic device according to claim 28 or 29, wherein: The predetermined condition includes that the federated learning server receives a list including the IDs of the partial uploading clients from the core network and / or the accuracy of the global model in the previous round of training reaches a preset accuracy.

31. The electronic device according to any one of claims 28 to 30, wherein: The at least one memory and the computer program code are configured to, through the at least one processor, cause the electronic device to execute: Notification information about the partial parameters is received from the federated learning server.

32. The electronic device according to claim 31, wherein: The global model is a layered neural network model. The notification information includes location information of the partial parameters in the neural network model.

33. The electronic device according to any one of claims 28 to 32, wherein: The magnitude information is used as an input of UE communication analysis in the network data analysis function NWDAF, and the UE communication prediction output of the UE communication analysis includes a list with IDs of some uploading clients.

34. The electronic device according to any one of claims 28 to 33, wherein: The at least one memory and the computer program code are configured to, through the at least one processor, cause the electronic device to execute: receiving a computation offloading instruction from the federated learning server, indicating that the federated learning client is to perform computation offloading, so as to determine whether to perform the computation offloading, The computation offloading indication is sent by the core network to the federated learning server based on the residence time of all federated learning clients within the coverage of the federated learning server.

35. The electronic device according to claim 34, wherein: The computation offloading indication is sent by the core network when it is determined that the residence time is less than the preset training duration of the local model.

36. The electronic device according to claim 34 or 35, wherein: The residence time is a time interval calculated by the core network based on the ID of the federated learning server, a time ID used to characterize time, and the number of federated learning clients within the coverage area of ​​the federated learning server. The density of the user terminals is obtained.

37. The electronic device according to claim 36, wherein: The residence time is obtained by the core network based on the moving speed of the federated learning client.

38. A method for a federated learning server, comprising: sending magnitude information about the magnitude of parameters of the global model for federated learning to a core network to assist the core network in identifying a federated learning client that cannot upload all parameters of its local model from among a plurality of federated learning clients as a partial uploading client, and When predetermined conditions are met, aggregation is performed based on partial parameters of the local model received from the partial uploading client to obtain a global model in a current round of training of federated learning.

39. A method for a core network, comprising: Receive magnitude information about parameter magnitudes of a global model used for federated learning from a federated learning server to identify a federated learning client that cannot upload all parameters of its local model from a plurality of federated learning clients as a partial uploading client, so that when predetermined conditions are met, the federated learning server aggregates the partial parameters of the local model received from the partial uploading client to obtain a global model in a current round of training of the federated learning.

40. A method for a federated learning client, comprising: When a predetermined condition is met, partial parameters of a local model for federated learning are sent to a federated learning server, so that the federated learning server aggregates the local model based on the partial parameters to obtain a global model in a current round of training of the federated learning. The federated learning server sends magnitude information about the magnitude of parameters of the global model to the core network to assist the core network in identifying the federated learning client as a partial uploading client that cannot upload all parameters of its local model.

41. A computer-readable storage medium having computer-executable instructions stored thereon, which, when executed, perform the method according to any one of claims 38 to 40.

Images