Computer system, learning method, and edge device

Abstract

To provide federated learning in consideration of a communication state between an edge device and a server.SOLUTION: A computer system comprises: an edge device which acquires data to be used for learning and uses the data to execute a learning process for generating a first model to be used to make an inference about a task; and a server device which generates a second model by using first models generated by a plurality of edge devices, respectively, and transmits the second model to the plurality of edge devices. The edge device acquires communication state information relating to a communication state of a communication path between the edge device and the server device, calculates a parameter to be used for a reduction process for reducing model data size on the basis of the communication state information, executes the reduction process on the first model on the basis of the parameter, and transmits the reduced first model to the server device.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to associative learning. [Background technology]

[0002] Since a large amount of data is required to train a model for inference of a task, one possible method is to collect data from multiple organizations or multiple locations. However, collecting data is difficult from the perspective of protecting the privacy and security of personal information.

[0003] Federated learning has attracted attention as a method for generating generic models without directly collecting data. Federated learning is a learning method in which models are trained at each organization or site, and multiple models are aggregated and integrated to generate generic models. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2012-103879 A Summary of the Invention [Problem to be solved by the invention]

[0005] In federated learning, model information is transmitted and received between an edge device that learns a model and a server that aggregates and integrates the model. When the model information is large, there is a problem that the communication band between the edge device and the server becomes congested. To address this problem, a technology described in Patent Document 1 is known.

[0006] Patent Document 1 states that "the network coefficient compression device includes an inference unit and a learning unit. The inference unit outputs output values ​​of the hidden layer or output layer of the neural network for input data input to the input layer of the trained neural network. The learning unit learns the network coefficients using the input data and output values ​​as training data while performing lossy compression of the network coefficients of the neural network, and generates compressed network coefficients."

[0007] The conventional techniques such as Patent Document 1 do not take into consideration the communication state between the edge device and the server (for example, the availability of the communication band). Therefore, the conventional techniques may cause problems such as a tight communication band and failure to properly transmit and receive the model.

[0008] The present invention provides a system, device, and method for performing federated learning incorporating a model reduction technique that takes into account the communication state between edge devices and a server. [Means for solving the problem]

[0009] A representative example of the invention disclosed in the present application is as follows: That is, a computer system includes an edge device that acquires data to be used for learning and executes a learning process for generating a first model to be used for inference regarding a task using the data, and a server device that generates a second model using the first models generated by each of the plurality of edge devices and transmits the second model to the plurality of edge devices; the first model and the second model are neural networks, The edge device acquires communication state information regarding a communication state of a communication path between the edge device and the server device, calculates first parameters to be used in a reduction process for reducing a data size of a model based on the communication state information, performs the reduction process on the generated first model based on the first parameters, and transmits the first model after the reduction process to the server device. The server device determines the weight of the second model based on an algorithm that takes into account the average, mode, and maximum value of the weights of the first model received from each of the plurality of edge devices. do. Effect of the Invention

[0010] According to the present invention, in federated learning, the edge device can reduce a model taking into account the communication state between the edge device and the server, and transmit the reduced model to the server. Problems, configurations, and effects other than those described above will become apparent from the following description of the embodiments. [Brief description of the drawings]

[0011] [Figure 1] FIG. 1 is a diagram illustrating an example of the configuration of a computer system according to a first embodiment. [Diagram 2] FIG. 2 illustrates an example of a hardware configuration of an edge device according to a first embodiment. [Figure 3A] FIG. 2 is a diagram illustrating an example of a configuration of an inference unit according to the first embodiment. [Figure 3B] FIG. 2 is a diagram illustrating an example of a configuration of an inference unit according to the first embodiment. [Figure 4] 11 is a flowchart illustrating an example of a process executed by the edge device in federated learning according to the first embodiment. [Diagram 5] 11 is a flowchart illustrating an example of a process executed by the server device in the first embodiment in federated learning. [Figure 6] 11 is a flowchart illustrating an example of an inference process executed by the edge device according to the first embodiment. [Figure 7] FIG. 13 is a diagram illustrating a modified example of the functional configuration of the edge device. [Figure 8] FIG. 4 is a diagram showing an example of a screen displayed by the learning monitoring device of the first embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0012] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. However, the present invention is not to be interpreted as being limited to the description of the embodiment shown below. It will be easily understood by those skilled in the art that the specific configuration can be changed without departing from the concept or purpose of the present invention.

[0013] In the configurations of the invention described below, the same or similar configurations or functions are given the same reference numerals, and duplicated explanations are omitted.

[0014] In this specification, the terms "first," "second," "third," and the like are used to identify components and do not necessarily limit the number or order.

[0015] In order to facilitate understanding of the invention, the position, size, shape, range, etc. of each component shown in the drawings, etc. may not represent the actual position, size, shape, range, etc. Therefore, the present invention is not limited to the position, size, shape, range, etc. disclosed in the drawings, etc. EXAMPLES

[0016] Fig. 1 is a diagram illustrating an example of a configuration of a computer system according to a first embodiment. Fig. 2 is a diagram illustrating an example of a hardware configuration of an edge device according to a first embodiment.

[0017] The computer system is composed of a server device 100, multiple edge devices 101, a communication path monitoring device 102, and a learning monitoring device 103. The server device 100 and the edge device 101 communicate with each other via a communication path 105. The communication path monitoring device 102 is connected to the server device 100 and the edge device 101 via the communication path 105 or a network not shown. In addition, the learning monitoring device 103 is connected to the server device 100, the multiple edge devices 101, and the communication path monitoring device 102 via the communication path 105 or a network not shown.

[0018] The learning monitoring device 103 monitors the parameter settings and status of the server device 100, the multiple edge devices 101, and the communication path monitoring device 102. The learning monitoring device 103 presents the monitoring results via, for example, a screen 800 shown in FIG. 8. The screen 800 includes an edge device selection field 801, a monitoring result display field 802, and a message field 803. The edge device selection field 801 is a field for selecting the edge device 101 for which the monitoring results are to be referred to, and displays an icon representing the edge device 101 monitored by the learning monitoring device 103. The monitoring result display field 802 is a field for displaying the monitoring results (parameter settings and status) of the edge device 101 selected in the edge device selection field 801. The message field 803 is a field for displaying a message indicating the status of the computer system.

[0019] The server device 100 and the multiple edge devices 101 are configured to perform federated learning. In the federated learning, the edge device 101 collects local data, learns a model using the local data, and transmits the local model to the server device 100. In addition, the server device 100 generates a global model using the local model, and transmits the global model to the edge device 101.

[0020] The communication path monitoring device 102 monitors the communication state of the communication path 105. Here, the communication state of the communication path 105 indicates communication latency, throughput, utilization rate of communication resources such as radio frequency bands, and their probabilistic distributions, etc. These communication states may change over time.

[0021] 2, and includes a processor 201, a main storage device 202, a secondary storage device 203, and a network interface 204. The hardware elements are connected to each other via an internal bus 205.

[0022] The processor 201 executes a program stored in the main memory device 202. The processor 201 executes processing according to the program, thereby operating as a functional unit (module) that realizes a specific function. For example, the processor 201 is a central processing unit (CPU), a graphics processing unit (GPU), a field-programmable gate array (FPGA), an application specific integrated circuit (ASIC), etc. In the following description, when processing is described with a functional unit as the subject, it indicates that the processor 201 is executing a program that realizes the functional unit.

[0023] The main memory device 202 is, for example, a dynamic random access memory (DRAM), and stores programs executed by the processor 201 and data used by the programs. The main memory device 202 is also used as a work area.

[0024] The secondary storage device 203 is a hard disk drive (HDD) or a solid state drive (SSD), and stores data permanently. The programs and data stored in the main storage device 202 may be stored in the secondary storage device 203. In this case, the processor 201 reads out the programs and information from the secondary storage device 203 and loads them into the main storage device 202.

[0025] The network interface 204 is an interface for connecting to an external device via a network.

[0026] The hardware configuration of the edge device 101 is merely an example and is not limited thereto. The edge device 101 may have input devices such as a keyboard, a mouse, a touch panel, etc., and may also have output devices such as a display and a printer. The edge device 101 may also be virtually realized as a program in the server device 100.

[0027] The hardware configurations of the server device 100 and the communication path monitoring device 102 are the same as those of the edge device 101, so a description thereof will be omitted.

[0028] The server device 100 has, as its functional components, a transmitting / receiving unit 110, a local model reducing unit 111, a reduction setting unit 112, a global model generating unit 113, and a global model reducing unit 114.

[0029] The transmitting / receiving unit 110 controls transmission and reception of data between the server device 100 and an external device. The local model reduction unit 111 reduces the local model received from the edge device 101. The reduction setting unit 112 sets parameters that determine the degree of reduction of the local model based on the communication state of the communication path 105. The parameters are set for each edge device 101. The global model generation unit 113 generates a global model using local models received from multiple edge devices 101. The global model reduction unit 114 reduces the global model generated by the global model generation unit 113 based on the parameters set by the reduction setting unit 112, and transmits the reduced global model to the edge device 101. The global model is reduced for each edge device 101.

[0030] The server device 100 may include a local model reduction unit 111 for each edge device 101 .

[0031] The edge device 101 has, as its functional components, a transmission / reception unit 120, a reduction setting unit 121, a learning unit 122, a local model reduction unit 123, and an inference unit .

[0032] The transmitting / receiving unit 120 controls transmission and reception of data between the edge device 101 and an external device. The reduction setting unit 121 sets parameters that determine the degree of reduction of the local model based on the communication state of the communication path 105. The learning unit 122 executes a learning process using the local data. The local model reduction unit 123 reduces the local model generated by the learning unit 122 based on the parameters set by the reduction setting unit 121, and transmits the reduced model to the server device 100. The inference unit 124 performs task inference using the global model and task data received from the server device 100.

[0033] Here, various configurations are possible for the inference unit 124. Figures 3A and 3B are diagrams illustrating an example of the configuration of the inference unit 124 according to the first embodiment.

[0034] The inference unit 124 in FIG. 3A includes a feature extraction unit 300 and a task inference unit 301. The feature extraction unit 300 extracts features from task data. The task inference unit 301 performs task inference using the features and outputs an inference result. The inference unit 124 in FIG. 3A requires a model (feature extraction model) used by the feature extraction unit 300 and a model (task inference model) used by the task inference unit 301. In this case, the two models may be treated as models (local models) to be subjected to associative learning, or one of the models may be treated as a local model. In the case of the inference unit 124 configured as shown in FIG. 3A, the learning unit 122 may be divided into learning units that generate each model.

[0035] The inference unit 124 in Fig. 3B includes a task inference unit 310. The task inference unit 310 performs task inference using task data and outputs an inference result. The inference unit 124 in Fig. 3B requires a model (task inference model) to be used by the task inference unit 310. In this case, the model is treated as a local model.

[0036] In addition, with respect to each functional unit of the server device 100, multiple functional units may be integrated into one functional unit, or one functional unit may be divided into multiple functional units for each function. In addition, with respect to each functional unit of the edge device 101, multiple functional units may be integrated into one functional unit, or one functional unit may be divided into multiple functional units for each function.

[0037] Next, the details of the federated learning in this embodiment will be described. The federated learning is performed in the following manner.

[0038] (1) The edge device 101 generates a model by executing a learning process using local data. The local data may be data acquired from devices and sensors connected to the edge device 101, or may be data acquired from a simulator. The edge device 101 may be virtually realized as a program in the server device 100. The edge device 101 may be a combination of a plurality of the above configurations. (2) The edge device 101 transmits, from among the generated models, a model to be subjected to federated learning as a local model to the server device 100. (3) The server device 100 generates a global model using a plurality of local models, and transmits the global model to each edge device 101. (4) The edge device 101 sets the global model as the initial local model, and executes the learning process again. Thereafter, the processes from (2) to (4) are repeatedly executed.

[0039] The processing of the edge device 101 and the server device 100 in federated learning will be described in detail below.

[0040] FIG. 4 is a flowchart illustrating an example of a process executed by the edge device 101 in federated learning according to the first embodiment.

[0041] The edge device 101 acquires communication state information from the communication path monitoring device 102 (step S101).

[0042] The reduction setting unit 121 of the edge device 101 calculates a reduction rate based on the communication state information (step S102).

[0043] For example, the reduction setting unit 121 manages the condition of the time required for transferring the local model, and calculates the reduction ratio based on the condition, the communication throughput, the communication latency, etc. Furthermore, the reduction setting unit 121 calculates a parameter for reducing the model based on the reduction ratio. The parameter is, for example, a threshold value. Note that the reduction ratio and the parameters related to the model reduction ratio may be updated in accordance with the communication state information that changes over time.

[0044] The learning unit 122 of the edge device 101 sets the learning process (step S103). Specifically, an initial model is set, and various parameters used in the learning process are set. Here, the initial model may be only the initial local model, or may include the initial local model and other models. When a global model has been received from the server device 100, the global model is set as the initial local model.

[0045] The learning unit 122 also performs settings to promote sparsification of the model. For example, an L1 regularization term or an L2 regularization term is added to the loss function. In addition, a regularization term that imposes a penalty when the absolute value of the weight is equal to or less than a threshold may be added.

[0046] The learning unit 122 of the edge device 101 executes a learning process (step S104). Since the learning process is a known technique, a detailed description thereof will be omitted. The model generated by the learning process is, for example, a neural network.

[0047] In the case of the inference unit 124 having the configuration shown in Fig. 3A, a feature extraction model and a task inference model are generated. The feature extraction model can be generated using, for example, an autoencoder, a variational autoencoder (VAE), a vector quantised-variational autoencoder (VQ-VAE), and contrastive learning such as SimCLR (Simple framework for Contrastive Learning of visual Representations) and BYOL (Bootstrap Your Own Latent).

[0048] In addition, when the subject of the associative learning is only the feature extraction model, the learning unit 122 may learn only the feature extraction model until the learning of the feature extraction model by associative learning is completed, and after the learning of the feature extraction model by associative learning is completed, the learning unit 122 may learn the task inference model using the feature extraction model and the learning data.

[0049] The local model reduction unit 123 of the edge device 101 reduces the local model generated by the learning process based on the parameters calculated by the reduction setting unit 121 (step S105). For example, the following reduction method is possible.

[0050] (Reduction Method 1) The local model reduction unit 123 acquires weight information of the model. The local model reduction unit 123 replaces the weight whose absolute value is equal to or less than a threshold with 0.

[0051] (Reduction method 2) The local model reduction unit 123 acquires weight information of the model. The weights are rearranged in descending order of absolute value. The local model reduction unit 123 replaces a predetermined number of weights with 0 in ascending order of absolute value so that the ratio of the number of non-zero weights to the total number of weights becomes a threshold value.

[0052] By increasing the number of zero-valued weights, the data size of the model can be reduced.

[0053] The local model reduction unit 123 of the edge device 101 transmits the reduced local model to the server device 100 (step S106).

[0054] FIG. 5 is a flowchart illustrating an example of a process executed by the server device 100 in the first embodiment in federated learning.

[0055] The local model reduction unit 111 of the server device 100 reduces the local model received from the edge device 101 (step S201). It is assumed that parameters used for reduction are set in advance. If local models have not been received from all edge devices 101, the server device 100 does not proceed to step S201 and waits.

[0056] When the local models are received from all edge devices 101, the global model generation unit 113 of the server device 100 generates a global model using the multiple local models (step S202). For example, the global model generation unit 113 calculates the weights using equation (1).

[0057]

number

[0058] Here, w i represents the weight information (weight vector) of the local model received from the i-th edge device 101, and a1, a2, and a3 represent coefficients. Note that i is a natural number from 1 to N. Furthermore, the mode function is a function that outputs the most frequent value, and the max function is a function that outputs the maximum value.

[0059] Equation (1) is a formula for calculating the weight of the global model, taking into account the mode and maximum values ​​of the weight.

[0060] The server device 100 acquires communication state information of each communication path 105 (step S203).

[0061] The reduction setting unit 112 of the server device 100 calculates a reduction rate based on the communication state information of each communication path 105 (step S204).

[0062] The reduction setting unit 112 manages the condition of the time required for the transfer of the global model, and calculates the reduction ratio of each edge device 101 based on the condition and the throughput of each communication path 105. Furthermore, the reduction setting unit 121 calculates a parameter for reducing the model based on the reduction ratio. The parameter is, for example, a threshold value.

[0063] The global model reduction unit 114 of the server device 100 reduces the global model based on the parameters of each edge device 101 (step S205). The method of reducing the model is the same as the method described in step S105. Here, the global model is reduced for each edge device 101.

[0064] The global model reduction unit 114 of the server device 100 transmits the reduced global model to each edge device 101 (step S206).

[0065] Next, a description will be given of an inference process executed by the edge device 101. Fig. 6 is a flowchart illustrating an example of the inference process executed by the edge device 101 of the first embodiment.

[0066] The inference unit 124 acquires information about the model generated by the learning unit 122 (step S301), and also acquires task data (step S302).

[0067] The inference unit 124 performs inference using the model and the task data (step S303), and outputs the inference result (step S304). Specifically, the inference unit 124 obtains the inference result by inputting the task data into the model.

[0068] In addition, the computer system may be one in which at least one of the local model and the global model is reduced. In addition, at least one of the server device 100 and the edge device 101 may have the function of the communication path monitoring device 102.

[0069] A specific example of the computer system described in the first embodiment will be described below.

[0070] (Case 1) A system for monitoring and controlling power consumption in a factory The edge device 101 is communicatively connected to devices and sensors operating in the factory. The edge device 101 also holds a feature extraction model that outputs a feature vector representing the features of the power usage status from data acquired from the devices and sensors, and a task inference model that uses the feature vector to output a predicted value of power usage or a control policy for reducing power consumption.

[0071] (Case 2) A system for controlling the allocation of manufacturing work in a factory The edge device 101 is communicatively connected to devices and sensors operating in the factory. The edge device 101 also holds a feature extraction model that outputs a feature vector representing the characteristics of the work performed by the devices from data acquired from the devices and sensors, and a task inference model that outputs a work allocation policy for robots using the feature vector.

[0072] (Case 3) A system for controlling manufacturing operations in a factory The edge device 101 is communicably connected to devices and sensors operating in a factory. The edge device 101 also holds a feature extraction model that outputs a feature vector representing the state of the work performed by the device (e.g., the force with which a robot arm grips a workpiece) from data acquired from the device and the sensor, and a task inference model that outputs a control value for the device using the feature vector.

[0073] (Case 4) System for monitoring abnormalities in factory equipment The edge device 101 is communicably connected to equipment and sensors in the factory. The edge device 101 also holds a feature extraction model that outputs a feature vector representing the operating state of the equipment from data acquired from the equipment and sensors, and a task inference model that outputs the presence or absence of an abnormality in the equipment and the details thereof using the feature vector.

[0074] (Case 5) A system that outputs the cause of equipment abnormalities in a factory The edge device 101 is communicably connected to equipment and sensors in the factory. The edge device 101 also holds a feature extraction model that outputs a feature vector representing the occurrence state of an abnormality in the equipment (e.g., the presence or absence of electrical noise, an abnormality in the number of rotations of a moving part, etc.) from data acquired from the equipment and sensors, and a task inference model that outputs the cause of the equipment abnormality using the feature vector.

[0075] (Case 6) System for managing product quality in a factory The edge device 101 is communicatively connected to equipment and sensors that perform inspections in the factory. The edge device 101 also holds a feature extraction model that outputs a feature vector representing a product state from data acquired from the equipment and sensors, and a task inference model that outputs the product quality using the feature vector.

[0076] (Case 7) System for managing communication quality in a communication network The edge device 101 is communicatively connected to communication devices such as transceivers / node devices in optical and wireless communication networks or sensors provided in the communication devices. The edge device 101 also holds a feature extraction model that outputs a feature vector representing the state of the communication device or a communication path to which the communication device is connected from data acquired from the communication device and the sensor, and a task inference model that outputs the quality of the communication device or the communication path to which the communication device is connected using the feature vector.

[0077] (Modification) The edge device 101 may execute processing using the inference result. For example, a functional configuration as shown in FIG. 7 is conceivable. The edge device 101 holds a document DB 126 that stores data in which documents and search keys are associated with each other, and also has a document search unit 125 that searches for documents from the document DB 126. The inference unit 124 outputs an estimated key from task data including images, documents, etc. The document search unit 125 calculates a score that evaluates the similarity between the estimated key output from the inference unit 124 and the search key registered in the document DB 126, and searches for related documents based on the score.

[0078] For example, data in which a search key indicating the operating state of an appliance is associated with a document describing a countermeasure or improvement measure according to the operating state of the appliance may be registered in the document DB 126. In this case, the inference unit 124 outputs an estimated key indicating the operating state of the appliance from task data including a value related to the appliance operation, and the document search unit 125 outputs the related document. This makes it possible to obtain information related to the appliance.

[0079] As described above, according to the present invention, in federated learning, a model can be reduced depending on the communication situation, and the model can be transmitted and received between the server device 100 and the edge device 101. This makes it possible to reduce the communication load in federated learning.

[0080] The present invention is not limited to the above-mentioned embodiment, but includes various modified examples. For example, the above-mentioned embodiment describes the configuration in detail to easily explain the present invention, and the present invention is not necessarily limited to the configuration including all the described configurations. Also, it is possible to add, delete, or replace a part of the configuration of each embodiment with another configuration.

[0081] Representative aspects of the invention other than those described in the claims are as follows: (1) A server device connected to an edge device that acquires data to be used for learning and executes a learning process for generating a first model to be used for inference regarding a task using the data, generating a second model using the first model generated by each of the plurality of edge devices; acquiring communication status information regarding a communication status of a communication path between the edge device and the server device; Calculating parameters to be used in a reduction process for reducing the data size of the model based on the communication state information; performing the reduction process on the generated second model based on the parameters; A server device, characterized in that the second model on which the reduction processing has been performed is transmitted to the edge device. (2) A server device according to (1), the first model and the second model are neural networks, The server device is characterized in that it determines the weight of the second model based on an algorithm that takes into account the average, mode, and maximum value of the weights of the first model received from each of the multiple edge devices. (3) A server device according to (1), the edge device generates, in the learning process, a feature extraction model that extracts feature information from the data and a task inference model that performs inference regarding the task using the feature information; The server device, wherein the first model is the feature extraction model.

[0082] In addition, each of the above configurations, functions, processing units, processing means, etc. may be realized in part or in whole by hardware, for example, by designing them as integrated circuits. The present invention can also be realized by software program code that realizes the functions of the embodiments. In this case, a storage medium on which the program code is recorded is provided to a computer, and a processor included in the computer reads the program code stored in the storage medium. In this case, the program code itself read from the storage medium realizes the functions of the above-mentioned embodiments, and the program code itself and the storage medium storing it constitute the present invention. Examples of storage media for supplying such program code include flexible disks, CD-ROMs, DVD-ROMs, hard disks, SSDs (Solid State Drives), optical disks, magneto-optical disks, CD-Rs, magnetic tapes, non-volatile memory cards, ROMs, etc.

[0083] Furthermore, the program code for realizing the functions described in this embodiment can be implemented in a wide range of program or script languages, such as assembler, C / C++, perl, Shell, PHP, Python, Java (registered trademark), etc.

[0084] Furthermore, the program code of the software that realizes the functions of the embodiments may be distributed over a network and stored in a storage means such as a computer's hard disk or memory, or in a storage medium such as a CD-RW or CD-R, and the processor of the computer may read out and execute the program code stored in the storage means or storage medium.

[0085] In the above-mentioned embodiment, the control lines and information lines are shown as those considered necessary for the explanation, and not all the control lines and information lines are shown in the product. All the components may be connected to each other. [Explanation of symbols]

[0086] 100 Server device 101 Edge Device 102 Communication path monitoring device 103 Learning monitoring device 105 Communication Channel 110 Transmitter / receiver 111 Local Model Reduction Section 112 Reduction setting section 113 Global Model Generation Unit 114 Global Model Reduction Section 120 Transmitter / receiver 121 Reduction setting section 122 Learning Department 123 Local Model Reduction Part 124 Reasoning part 125 Document Search Unit 126 Document DB 201 Processor 202 Main storage 203 Secondary storage device 204 Network Interface 205 Internal Bus 300 Feature Extraction Unit 301, 310 Task Reasoning Section 800 screens

Claims

1. 1. A computer system comprising: an edge device that acquires data to be used for learning and executes a learning process to generate a first model to be used for inference regarding a task using the data; a server device that generates a second model using the first model generated by each of the plurality of edge devices and transmits the second model to the plurality of edge devices; Equipped with the first model and the second model are neural networks, The edge device includes: acquiring communication status information regarding a communication status of a communication path between the edge device and the server device; Calculating a first parameter to be used in a reduction process for reducing a data size of the model based on the communication state information; performing the reduction process on the generated first model based on the first parameters; transmitting the first model on which the reduction process has been performed to the server device; A computer system characterized in that the server device determines the weight of the second model based on an algorithm that takes into account the average, mode, and maximum value of the weights of the first model received from each of the multiple edge devices.

2. 2. The computer system of claim 1, The server device includes: Acquire the communication status information; Calculating a second parameter to be used in the reduction process based on the communication state information; performing the reduction process on the generated second model based on the second parameters; and transmitting the second model on which the reduction process has been performed to the edge device.

3. A computer system as claimed in claim 1, The edge device includes: In the learning process, a feature extraction model that extracts feature information from the data and a task inference model that performs inference regarding the task using the feature information are generated; The first model is the feature extraction model.

4. A learning method in a computer system, comprising: The computer system includes an edge device that acquires data to be used for learning and executes a learning process to generate a first model to be used for inference regarding a task using the data, and a server device that generates a second model using the first model generated by each of the plurality of edge devices and transmits the second model to the plurality of edge devices; the first model and the second model are neural networks, The learning method includes: The edge device acquires communication status information regarding a communication status of a communication path between the edge device and the server device; A step in which the edge device calculates a first parameter to be used in a reduction process for reducing a data size of a model based on the communication state information; the edge device performing the reduction process on the generated first model based on the first parameters; a step of transmitting the first model, on which the reduction process has been performed, to the server device by the edge device; and a step in which the server device determines a weight for the second model based on an algorithm that takes into account the average, mode, and maximum value of the weights of the first model received from each of the plurality of edge devices.

5. A learning method according to claim 4, The server device acquires the communication status information; a step of calculating a second parameter to be used in the reduction process based on the communication state information by the server device; The server device executes the reduction process on the generated second model based on the second parameters; the server device transmitting the second model on which the reduction process has been performed to the edge device.

6. A learning method according to claim 4, The edge device generates a feature extraction model that extracts feature information from the data, and a task inference model that uses the feature information to perform inference regarding the task, The learning method, wherein the first model is the feature extraction model.

7. An edge device that acquires data to be used for learning, and executes a learning process to generate a first model to be used for inference regarding a task using the data, A processor, a memory connected to the processor, and a network interface connected to the processor, a server device that generates a second model using the first model generated by each of a plurality of edge devices and transmits the second model to the plurality of edge devices; the first model and the second model are neural networks, the weight of the second model is determined by the server device based on an algorithm that takes into account an average, a mode, and a maximum value of the weights of the first model received from each of the plurality of edge devices; The edge device includes: acquiring communication status information regarding a communication status of a communication path between the edge device and the server device; Calculating parameters to be used in a reduction process for reducing the data size of the model based on the communication state information; performing the reduction process on the generated first model based on the parameters; The edge device transmits the first model on which the reduction process has been performed to the server device.

8. An edge device as claimed in claim 7, In the learning process, a feature extraction model that extracts feature information from the data and a task inference model that performs inference regarding the task using the feature information are generated; The edge device, wherein the first model is the feature extraction model.

Images