Learning device, learning system, learning method, and program

Abstract

Provided are a learning device, a learning system, a learning method, and a program capable of building a global model in a case where a plurality of organization networks are not constantly connected. A learning device (1) comprises: a communication establishment unit (11) that establishes secure communications with information terminals (2) arranged in networks (N) of the respective organizations; an acquisition unit (12) that acquires a data set for each organization from the information terminals (2) by using secure communications; a learning unit (13) that causes a local model to learn the data set; and an integration unit (14) that integrates the plurality of local models which have learned the plurality of data sets.

Description

Learning device, learning system, learning method, and computer-readable medium

[0001] The present disclosure relates to a learning device, a learning system, a learning method, and a computer-readable medium.

[0002] Patent Literature 1 discloses a technique for performing machine learning to build an AI (Artificial Intelligence) model (also called a local model) personalized for a user.

[0003] Special Publication No. 2020-531999

[0004] It is known that integrating multiple local AI models can build a better AI model (also called a global model). The server collects user data, allowing the server to build the local model and the global model.

[0005] When the user is an organization, it is desirable to build a network that connects multiple organizations because it is necessary to collect data owned by each organization. However, there is a problem in that it is difficult to build a network that connects multiple organizations with different security concepts.

[0006] Therefore, one of the objectives that the embodiments disclosed in this specification aim to achieve is to provide a learning device, a learning system, a learning method, and a computer-readable medium that can build a global model when the networks of multiple organizations are not always connected to each other.

[0007] A learning device according to a first aspect of the present disclosure includes a communication establishment means for establishing secure communication with an information terminal located on a network of each organization; an acquisition means for acquiring a dataset for each organization from the information terminal using the secure communication; a learning means for training a local model on the dataset; and an integration means for integrating multiple local models trained on multiple datasets.

[0008] A computing system according to a second aspect of the present disclosure is a learning system comprising: an information terminal disposed in a network of each organization; and a learning device, wherein the learning device establishes secure communication with the information terminal, acquires a dataset for each organization from the information terminal using the secure communication, trains a local model on the dataset, and integrates multiple local models trained on multiple datasets.

[0009] In a calculation method according to a third aspect of the present disclosure, a computer establishes secure communication with an information terminal located on a network of each organization, acquires a dataset for each organization from the information terminal using the secure communication, trains a local model on the dataset, and integrates multiple local models trained on multiple datasets.

[0010] A non-transitory computer-readable medium according to a fourth aspect of the present disclosure stores a program for causing a computer to execute the following processes: establishing secure communication with an information terminal located in each organization's network; acquiring a dataset for each organization from the information terminal using the secure communication; training a local model on the dataset; and integrating multiple local models trained on multiple datasets.

[0011] According to the present disclosure, it is possible to provide a learning device, a learning system, a learning method, and a computer-readable medium that are capable of building a global model when the networks of multiple organizations are not always connected to each other.

[0012] Fig. 1 is a block diagram showing the configuration of a learning device according to embodiment 1. Fig. 2 is a block diagram showing the configuration of a learning system according to embodiment 2. Fig. 3 is a block diagram showing the configuration of a learning device according to embodiment 2. Fig. 4 is a flowchart showing the flow of an operation for generating a local model. Fig. 5 is a block diagram showing the configuration of a learning system according to embodiment 2.

[0013] First Embodiment Fig. 1 is a block diagram showing the configuration of a learning device 1 according to a first embodiment. The learning device 1 includes a communication establishment unit 11, an acquisition unit 12, a learning unit 13, and an integration unit 14. The learning device 1 is connected to a public network (not shown). The public network is connected to the networks of each organization. An information terminal (not shown) is disposed in each organization's network. The information terminal is a repository in which data sets owned by each organization are stored.

[0014] The communication establishment unit 11 establishes secure communication with an information terminal located on the network of each organization. The communication establishment unit 11 may establish secure communication at a predetermined timing. The communication establishment unit 11 may also establish secure communication based on the progress of learning of a local model, which will be described later.

[0015] For example, the communication establishment unit 11 connects the learning device 1 to each organization's network via a VPN (Virtual Private Network). In this case, confidentiality of communication between the learning device 1 and the information terminal is maintained by encryption and encapsulation. In other words, secure communication is established between the learning device 1 and the information terminal.

[0016] The communication establishment unit 11 may establish secure communication using a technology other than VPN. The communication establishment unit 11 may control communication using a protocol including encryption (e.g., SSL / TLS, SSH (Secure Shell), FTPS (File Transfer Protocol over SSL / TLS)).

[0017] The acquisition unit 12 acquires a data set for each organization from an information terminal using secure communication.

[0018] The learning unit 13 trains the local model on the data set.

[0019] The integration unit 14 integrates a plurality of local models trained on a plurality of data sets.

[0020] The learning device 1 includes a processor, memory, and storage device (not shown). The storage device stores a computer program that implements the processing of the learning method according to this embodiment. The processor then loads the computer program from the storage device into the memory and executes the computer program. This allows the processor to realize the functions of a communication establishment unit 11, an acquisition unit 12, a learning unit 13, and an integration unit 14.

[0021] Alternatively, the communication establishment unit 11, the acquisition unit 12, the learning unit 13, and the integration unit 14 may each be realized by dedicated hardware. Furthermore, some or all of the components of each device may be realized by general-purpose or dedicated circuits, processors, etc., or a combination thereof. These may be configured by a single chip, or by multiple chips connected via a bus. Some or all of the components of each device may be realized by a combination of the above-mentioned circuits, etc., and a program. Furthermore, a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), an FPGA (Field-Programmable Gate Array), etc. may be used as the processor.

[0022] Furthermore, when some or all of the components of the learning device 1 are implemented using multiple information processing devices, circuits, etc., the multiple information processing devices, circuits, etc. may be centrally or decentralized. For example, the information processing devices, circuits, etc. may be implemented as a client-server system, cloud computing system, or other system connected via a communication network. Furthermore, the functions of the learning device 1 may be provided in the form of SaaS (Software as a Service).

[0023] The learning device according to the first embodiment establishes secure communication with an information terminal connected to the network of each organization and acquires a dataset using the secure communication. Therefore, according to the first embodiment, a global model can be constructed even when the networks of multiple organizations are not always connected to each other.

[0024] <Embodiment 2> Embodiment 2 is a specific example of embodiment 1. Fig. 2 is a schematic diagram showing the configuration of a learning system 100 according to embodiment 2. Learning system 100 includes information terminal 2a, information terminal 2b, information terminal 2c, VPN device 3a, VPN device 3b, VPN device 3c, and learning device 4. Learning device 4 is a specific example of the learning device 1 described above.

[0025] An information terminal 2a and a VPN device 3a are arranged in a network Na of organization A. An information terminal 2b and a VPN device 3b are arranged in a network Nb of organization B. An information terminal 2c and a VPN device 3c are arranged in a network Nc of organization C.

[0026] A data set owned by organization A is stored in information terminal 2a. A data set owned by organization B is stored in information terminal 2b. A data set owned by organization C is stored in information terminal 2c.

[0027] The number of organizations is not limited to three. It may be two, four, or more. Each organization is, for example, a pharmaceutical manufacturer or a chemical manufacturer. In this case, the dataset is a dataset of compounds. Each record included in the dataset of compounds lists structural information and property information of the compound. The structure of the compound is expressed as a fixed-length bit string, and each bit in the bit string indicates the presence or absence of a specific structure (e.g., a benzene ring). Property values ​​(e.g., tensile strength) may be values ​​obtained through experiments, simulations, or theoretical calculations. For example, data generated daily in research and development activities of organization A is stored in information terminal 2a. Of course, the dataset is not limited to a dataset of compounds, but may be a dataset of any object.

[0028] When the information terminals 2a, 2b, and 2c are not distinguished from one another, they may be simply referred to as information terminals 2. When the networks Na, Nb, and Nc are not distinguished from one another, they may be simply referred to as network N. The network N may be a LAN (Local Area Network) or a network in which multiple LANs are connected. The network N is connected to a public network PN such as the Internet.

[0029] The VPN device 3 is a VPN server or a router compatible with VPN. The IP (Internet Protocol) address of the learning device 4 may be set in advance in the VPN device 3. The VPN may be an Internet VPN, an IP-VPN, or a wide area Ethernet. When the VPN devices 3a, 3b, and 3c are not to be distinguished from one another, they may be simply referred to as the VPN device 3.

[0030] 3 is a block diagram illustrating the configuration of the learning device 4. The learning device 4 is connected to the network PN. The learning device 4 includes a communication establishment unit 41, an acquisition unit 42, a learning unit 43, and an integration unit 44.

[0031] The learning device 4 includes storage for storing local models La, Lb, and Lc. Local model La is a local model trained on a dataset owned by organization A. Local model Lb is a local model trained on a dataset owned by organization B. Local model Lc is a local model trained on a dataset owned by organization C. Local models La, Lb, and Lc are repeatedly updated by the learning unit 43. When local models La, Lb, and Lc are not to be distinguished from one another, they may be simply referred to as local model L.

[0032] The communication establishment unit 41 is a specific example of the communication establishment unit 11 described above. The communication establishment unit 41 establishes secure communication with the information terminal 2. Specifically, the communication establishment unit 41 connects to a VPN device 3, such as a VPN server, via the public network PN and requests a VPN connection from the VPN device 3. First, a TCP / IP connection is established between the learning device 4 and the VPN device 3. Then, the learning device 4 is authenticated, and a VPN session is established between the learning device 4 and the VPN device 3. After the acquisition unit 42 acquires the data set, the communication establishment unit 41 terminates the VPN session. The learning device 4 may be connected to the network N via a remote access VPN.

[0033] The timing at which the communication establishment unit 41 establishes secure communication, i.e., the timing at which the learning device 4 connects to the network N via VPN, will be described later. This is because the timing may be related to the progress of processing in the learning unit 43, which will be described later. The timing at which secure communication is established with the information terminal 2a, the timing at which secure communication is established with the information terminal 2b, and the timing at which secure communication is established with the information terminal 2c may be different from one another.

[0034] The acquisition unit 42 is a specific example of the above-mentioned acquisition unit 12. The acquisition unit 42 acquires a data set from the information terminal 2 after the learning device 4 is connected to the network N via VPN.

[0035] The learning unit 43 is a specific example of the above-mentioned learning unit 13. The learning unit 43 causes the corresponding local model L to learn the data set acquired by the acquisition unit 42.

[0036] The integrating unit 44 is a specific example of the integrating unit 14 described above. The integrating unit 44 integrates the local models La, Lb, and Lc learned by the learning unit 43. The integrated model is called a global model. The integrating unit 44 may integrate the local models La, Lb, and Lc at a predetermined timing (e.g., once a day, once every few months). The global model has higher performance than the local models La, Lb, and Lc. Furthermore, the integrating unit 44 may perform a process of integrating the local models La, Lb, and Lc after learning of the local models La, Lb, and Lc is completed.

[0037] The integrating unit 44 may generate the global model by, for example, taking the arithmetic mean of the model parameters of the local model La, the model parameters of the local model Lb, and the model parameters of the local model Lc. Note that the method for integrating the model parameters is not limited to the arithmetic mean.

[0038] After the integrator 44 generates the global model, the learning device 4 distributes the global model to the information terminals 2 a, 2 b, and 2 c. For example, after the process of generating the global model is completed, the learning device 4 may connect to the networks Na, Nb, and Nc in turn via VPN and transmit the global model to the information terminals 2 a, 2 b, and 2 c.

[0039] Furthermore, the learning device 4 may connect to the network N via VPN in response to a request from each information terminal 2 and transmit the global model to the information terminal 2. Each information terminal 2 can import the global model at any time. Organizations A, B, and C can utilize a high-performance global model that combines data sets owned by multiple organizations.

[0040] Constructing multiple local models L and integrating the multiple local models L is also called federated learning. In this case, it can be said that the learning device 4 is performing federated learning. However, it should be noted that constructing a local model L at local terminals such as information terminals 2a, 2b, and 2c is also sometimes called federated learning. In the second embodiment, the learning device 4 constructs the local model L.

[0041] The learning device 4 sequentially repeats the process of establishing secure communication, the process of acquiring a dataset, and the process of training a local model using the acquired dataset. This allows the performance of the global model to be improved based on the datasets accumulated daily in each information terminal 2. Note that the process of integrating multiple local models may be performed at any timing.

[0042] Next, the timing at which the communication establishment unit 41 establishes secure communication will be described. The communication establishment unit 41 may establish secure communication at a predetermined timing. The predetermined timing may be once every few months or once every few days.

[0043] Furthermore, the communication establishment unit 41 may establish secure communication in response to a request received from each information terminal 2. For example, the information terminal 2 transmits a request when the amount of accumulated data sets reaches or exceeds a predetermined amount.

[0044] The communication establishment unit 41 may establish the next secure communication based on the progress of learning in which the local model L learns the dataset. When one dataset is learned by the local model L, the dataset is divided into multiple batches, and the local model L learns the multiple batches in order. The process of dividing the dataset into batches and learning the multiple batches is repeated a predetermined number of times. The predetermined number of times is set so that the model parameters of the local model L converge. However, the predetermined number of times needs to be set to a small number that does not cause overlearning. The communication establishment unit 41 may establish the next secure communication when the model parameters of the local model have converged.

[0045] The progress of learning may be expressed as the number of learning iterations or the number of learned batches. For example, if a dataset is divided into five batches and learning is repeated 10 times, the next secure communication may be established when learning is complete, that is, when the tenth learning is completed. The communication establishment unit 41 may establish the next secure communication when learning is nearing completion, for example, when the fourth batch of the tenth learning is completed.

[0046] The communication establishment unit 41 may sequentially establish secure communications with the information terminals 2 a, 2 b, and 2 c when the learning progress of the local model La, the learning progress of the local model Lb, and the learning progress of the local model Lc exceed a threshold. Furthermore, when the learning progress of any one of the local models L exceeds a threshold, the communication establishment unit 41 may establish secure communications with the corresponding information terminal 2.

[0047] The communication establishment unit 41 may establish the next secure communication based on the progress of the process of integrating multiple local models L. If the process in the integrating unit 44 is not a simple arithmetic average or if there are a large number of organizations, the process by the integrating unit 44 may take a long time. It would be efficient if the next process could be started after the process in the integrating unit 44 has finished.

[0048] Furthermore, when a secure computation technique is applied, the processing by the integrating unit 44 may take a long time. It is known that the dataset used for learning can be inferred by reverse engineering the local model L. Therefore, in order to improve the confidentiality of the local model L, it is desirable to perform secure computation when integrating the local models L. Secure computation is a technique for performing computational processing while keeping data encrypted, and known secure computation techniques include multi-party computation (MPC) and homomorphic encryption.

[0049] 4 is a flowchart showing the flow of processing for generating a local model L. It is assumed that the learning device 4 stores an initial local model L (step S101).

[0050] Next, the communication establishment unit 41 of the learning device 4 determines whether it is time to establish secure communication (step S102). If it is not time to establish secure communication (NO in step S102), the process returns to step S102.

[0051] If it is time to establish secure communication (YES in step S102), the communication establishment unit 41 establishes secure communication between the information terminal 2 and the learning device 4, and the acquisition unit 42 acquires a data set from the information terminal 2 (step S103). Thereafter, the communication establishment unit 41 ends the secure communication.

[0052] In step S103, multiple data sets may be acquired. First, secure communication is established between information terminal 2a and learning device 4, the acquisition unit 42 acquires the data set from information terminal 2a, and the communication establishment unit 41 terminates the secure communication. Then, secure communication is established between information terminal 2b and learning device 4, the acquisition unit 42 acquires the data set from information terminal 2b, and the communication establishment unit 41 terminates the secure communication. Then, secure communication is established between information terminal 2c and learning device 4, the acquisition unit 42 acquires the data set from information terminal 2c, and the communication establishment unit 41 terminates the secure communication. Of course, in step S103, the data set may be acquired from any of information terminals 2a, 2b, and 2c.

[0053] Next, the learning unit 43 causes the local model L to learn the data set acquired in step S103, and updates the local model L (step S104). If multiple data sets are acquired in step S103, multiple local models L may be updated in step S104. After updating the local model L, the process returns to step S102. Note that the process of integrating multiple local models L may be performed at any timing.

[0054] The learning device according to the second embodiment connects to the network of each organization via VPN at appropriate communication timing to acquire the dataset of that organization, thereby enabling secure reception of the dataset and construction of a local model at appropriate timing.

[0055] Note that secure communication is not limited to communication via a VPN. Secure communication may be communication using any secure communication protocol (e.g., an encryption protocol). The data set may be sent from the information terminal 2 to the learning device 4 by email using a secure communication protocol (e.g., S / MIME).

[0056] <Modification of Second Embodiment> The device including the integration unit 44 that integrates the global model may be different from the device including the learning unit 43 that builds the local model L. In this case, the device including the integration unit 44 may establish secure communication (e.g., SSL) with the device including the learning unit 43 to acquire the local model L. This not only makes it possible to secure communication between the repository (e.g., information terminal 2) where the dataset is stored and the local model L, but also makes it possible to secure communication between the local model L and the global model.

[0057] <Third Embodiment> The third embodiment is a specific example of the second embodiment. The learning device according to the third embodiment integrates model parameters of local models using secure computation. Fig. 5 is a block diagram showing the configuration of a learning system 100a according to the third embodiment. Comparing Fig. 2 with Fig. 5, a server group 5 has been added.

[0058] The server group 5 includes a plurality of secure computation servers 51. The number of secure computation servers 51 is not limited to three. However, in order to perform secure computation, it is preferable that the number of secure computation servers 51 is three or more.

[0059] The server group 5 integrates the local model La, the local model Lb, and the local model Lc, and transmits the result of the secure computation to the learning device 4.

[0060] The integrating unit 44 of the learning device 4 divides the model parameters of the local model La into multiple shares (e.g., three) and transmits the multiple shares to the multiple secure computation servers 51. The integrating unit 44 divides the model parameters of the local model Lb into multiple shares and transmits the multiple shares to the multiple secure computation servers 51. The integrating unit 44 divides the model parameters of the local model Lc into multiple shares and transmits the multiple shares to the multiple secure computation servers 51.

[0061] Each secure computation server 51 uses the received shares to perform secure computation to calculate the global model. The local model cannot be discovered from the shares, and computation using the shares can be considered secure computation. Multiple secure computation servers 51 may cooperate to perform multi-party computation (MPC). Since the amount of computation required to integrate the local model L is sufficiently small, it is believed that the server group 5 can perform secure computation in a realistic amount of time.

[0062] The third embodiment also provides the same effects as the second embodiment. Furthermore, according to the third embodiment, the calculation for integrating the global model can be kept confidential.

[0063] The above-described program includes a set of instructions (or software code) that, when loaded into a computer, causes the computer to perform one or more functions described in the embodiments. The program may be stored in a non-transitory computer-readable medium or a tangible storage medium. By way of example and not limitation, computer-readable media or tangible storage media include random-access memory (RAM), read-only memory (ROM), flash memory, solid-state drive (SSD) or other memory technologies, CD-ROM, digital versatile disc (DVD), Blu-ray (registered trademark) disc or other optical disk storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage device. The program may also be transmitted on a transitory computer-readable medium or communication medium. By way of example and not limitation, transitory computer-readable media or communication media include electrical, optical, acoustic, or other forms of propagated signals.

[0064] Although the present invention has been described above with reference to the embodiments, the present invention is not limited to the above. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present invention within the scope of the invention.

[0065] Some or all of the above embodiments can be described as, but are not limited to, the following supplementary notes. (Supplementary Note 1) A learning device comprising: communication establishment means for establishing secure communication with an information terminal located on a network of each organization; acquisition means for acquiring a dataset for each organization from the information terminal using the secure communication; learning means for training a local model on the dataset; and integration means for integrating multiple local models trained on multiple datasets. (Supplementary Note 2) The learning device according to Supplementary Note 1, wherein the communication establishment means establishes the next secure communication based on the progress of learning of the local model. (Supplementary Note 3) The learning device according to Supplementary Note 1, wherein the communication establishment means establishes the next secure communication when model parameters of the local model have converged. (Supplementary Note 4) The learning device according to Supplementary Note 1, wherein the communication establishment means establishes the secure communication at a predetermined timing. (Supplementary Note 5) The learning device according to Supplementary Note 1, wherein the communication establishment means establishes the secure communication in response to receiving a request from each information terminal. (Supplementary Note 6) The learning device according to Supplementary Note 5, wherein the request is sent by the information terminal when the amount of data in the dataset stored in the information terminal exceeds a predetermined amount. (Supplementary Note 7) The learning device according to Supplementary Note 1, wherein the communication establishment means establishes the next secure communication based on the progress of the process of integrating the multiple local models. (Supplementary Note 8) The learning device according to Supplementary Note 7, wherein the integration means integrates the multiple local models using secure computing technology. (Supplementary Note 9) The learning device according to any one of Supplements 1 to 8, wherein the communication establishment means establishes the secure communication by connecting the learning device to the network via a VPN (Virtual Private Network).(Supplementary Note 10) A learning system comprising an information terminal arranged in a network of each organization and a learning device, wherein the learning device establishes secure communication with the information terminal, obtains a dataset for each organization from the information terminal using the secure communication, trains a local model on the dataset, and integrates multiple local models trained on multiple datasets. (Supplementary Note 11) The learning system according to Supplementary Note 10, wherein the learning device establishes a next secure communication based on the progress of learning in the local model. (Supplementary Note 12) A learning method, wherein a computer establishes secure communication with an information terminal arranged in a network of each organization, obtains a dataset for each organization from the information terminal using the secure communication, trains a local model on the dataset, and integrates multiple local models trained on multiple datasets. (Supplementary Note 13) A non-transitory computer-readable medium storing a program for causing a computer to execute the following processes: establishing secure communication with an information terminal located on each organization's network; acquiring a dataset for each organization from the information terminal using the secure communication; training a local model on the dataset; and integrating multiple local models trained on multiple datasets.

[0066] 1, 4 Learning device 11, 41 Communication establishment unit 12, 42 Acquisition unit 13, 43 Learning unit 14, 44 Integration unit 2, 2a, 2b, 2c Information terminal 3, 3a, 3b, 3c VPN device 100, 100a Learning system 5 Server group 51 Secure computation server N, Na, Nb, Nc Network PN Public network

Claims

1. Communication establishment means for establishing secure communication with an information terminal arranged in each organization's network; Acquisition means for acquiring a data set for each organization from the information terminal using the secure communication; Learning means for causing the local model to learn the data set; Integration means for integrating a plurality of local models that have learned a plurality of data sets A learning device comprising.

2. The communication establishment means establishes the next secure communication based on the progress of learning of the local model The learning device according to claim 1.

3. The communication establishment means establishes the next secure communication when the model parameters of the local model converge The learning device according to claim 1.

4. The communication establishment means establishes the secure communication at a predetermined timing The learning device according to claim 1.

5. The communication establishment means establishes the secure communication in response to receiving a request from each information terminal The learning device according to claim 1.

6. The request is transmitted when the data amount of the data set stored in the information terminal exceeds a predetermined amount The learning device according to claim 5.

7. The communication establishment means establishes the next secure communication based on the progress of the process of integrating the plurality of local models The learning device according to claim 1.

8. The integration means integrates the plurality of local models using secure computing technology The learning device according to claim 7.

9. The communication establishment means establishes the secure communication by connecting the learning device to the network via a VPN (Virtual Private Network) The learning device according to any one of claims 1 to 8.

10. An information terminal arranged in each organization's network; A learning device; A learning system comprising: The learning device is Establish secure communication with the information terminal, Acquire a data set for each organization from the information terminal using the secure communication, Cause the local model to learn the data set, Integrate a plurality of local models that have learned a plurality of data sets Learning system.

11. The learning device establishes the next secure communication based on the progress of learning in the local model The learning system according to claim 10.

12. A computer Establish secure communication with information terminals deployed in the networks of each organization, acquire a data set for each organization from the information terminal using the secure communication, let the local model learn the data set, integrate a plurality of local models that have learned a plurality of data sets Learning method.

13. On a computer, a process of establishing secure communication with information terminals deployed in the networks of each organization, a process of acquiring a data set for each organization from the information terminal using the secure communication, a process of letting the local model learn the data set, a process of integrating a plurality of local models that have learned a plurality of data sets A program for causing the above to be executed.