Learning devices, learning systems, learning methods, and programs

Abstract

Provided are a learning device, a learning system, a learning method, and a program with which a global model can be constructed when networks of multiple organizations are not always connected. A learning device (1) comprises a communication establishment unit (11) that establishes secure communication with information terminals (2) placed in networks (N) of organizations, an acquisition unit (12) that acquires a local model trained on a data set for each organization from the information terminals (2) using secure communication, and an integration unit (13) that integrates the multiple acquired local models.

Description

Technical Field

[0006]

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

Background Art

[0002] Patent Document 1 discloses a technique for performing machine learning to construct an AI (Artificial Intelligence) model (also referred to as a local model) individualized for a user.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] It is known that a better-performing AI model (also referred to as a global model) can be constructed by integrating a plurality of local AI models. By collecting user data on the server, the server can construct local models and global models.

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

[0006] Therefore, one of the purposes to be achieved by the embodiments disclosed in this specification is to provide a learning device, a learning system, a learning method, and a computer-readable medium capable of constructing a global model when the networks of multiple organizations are not always connected.

Means for Solving the Problems

[0007] The learning device relating to the first aspect of this disclosure is A means for establishing secure communication with information terminals located on the network of each organization, An acquisition means that uses the aforementioned secure communication to acquire a local model trained on a dataset for each organization from the information terminal, Integration means for combining multiple acquired local models It is equipped with.

[0008] The computing system relating to the second aspect of this disclosure is Information terminals located on each organization's network, Learning device, A learning system equipped with, The learning device is Secure communication is established with the aforementioned information terminal, Using the aforementioned secure communication, a local model trained on organization-specific datasets is acquired from the information terminal. Integrate the multiple local models that have been retrieved.

[0009] The calculation method relating to the third aspect of this disclosure, Computers Secure communication is established between information terminals located on each organization's network. Using the aforementioned secure communication, a local model trained on organization-specific datasets is obtained from the information terminal. Integrate the multiple local models that have been retrieved.

[0010] In the non-temporary computer-readable media relating to the fourth aspect of this disclosure, On the computer, The process of establishing secure communication with information terminals located on each organization's network, Using the aforementioned secure communication, the process involves obtaining a local model trained on a dataset specific to each organization from the information terminal, A process for integrating a plurality of acquired local models and A program for causing the process to be executed is stored.

Advantages of the Invention

[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 capable of constructing a global model even when networks of a plurality of organizations are not always connected.

Brief Description of the Drawings

[0012] [Figure 1] FIG. 1 is a block diagram showing the configuration of a learning device according to Embodiment 1. [Figure 2] FIG. 2 is a block diagram showing the configuration of a learning system according to Embodiment 2. [Figure 3] FIG. 3 is a block diagram showing the configuration of a learning device according to Embodiment 2. [Figure 4] FIG. 4 is a flowchart showing the flow of an operation for generating a local model. [Figure 5] FIG. 5 is a block diagram showing the configuration of a learning system according to Embodiment 2. [[ID=DO31]]

Modes for Carrying Out the Invention

[0013] <Embodiment 1> FIG. 1 is a block diagram showing the configuration of a learning device 1 according to Embodiment 1. The learning device 1 includes a communication establishment unit 11, an acquisition unit 12, and an integration unit 13. The learning device 1 is connected to a public network (not shown). Networks of each organization are connected to the public network (not shown). Information terminals (not shown) are arranged in the networks of each organization. The information terminal constructs a local model that has learned a dataset for each organization. The information terminal may be a repository in which datasets owned by each organization are accumulated.

[0014] The communication establishment unit 11 establishes secure communication with information terminals arranged in the networks of each organization. The communication establishment unit 11 may establish secure communication at a predetermined timing.

[0015] For example, the communication establishment unit 11 connects the learning device 1 to the networks of each organization via a VPN (Virtual Private Network). In this case, the communication between the learning device 1 and the information terminal is kept confidential by encryption and encapsulation. That is, secure communication is established between the learning device 1 and the information terminal.

[0016] Note that the communication establishment unit 11 may establish secure communication using technologies other than VPN. The communication establishment unit 11 may control communication by protocols including encryption (e.g., SSL / TLS, SSH (Secure Shell), FTPS (File Transfer Protocol over SSL / TLS)).

[0017] The acquisition unit 12 acquires local models learned from data sets for each organization from the information terminals using secure communication.

[0018] The integration unit 13 integrates the acquired multiple local models.

[0019] Note that the learning device 1 includes a processor, a memory, and a storage device as a configuration not shown. Further, a computer program in which the processing of the learning method according to the present embodiment is implemented is stored in the storage device. Then, the processor causes the memory to read the computer program from the storage device and executes the computer program. Thereby, the processor realizes the functions of the communication establishment unit 11, the acquisition unit 12, and the integration unit 13.

[0020] Alternatively, the communication establishment unit 11, the acquisition unit 12, and the integration unit 13 may each be implemented with dedicated hardware. Furthermore, some or all of the components of each device may be implemented by general-purpose or dedicated circuits, processors, etc., or combinations 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 implemented by a combination of the aforementioned circuits, etc., and programs. Furthermore, a CPU (Central Processing Unit), GPU (Graphics Processing Unit), FPGA (field-programmable gate array), etc., can be used as the processor.

[0021] Furthermore, if some or all of the components of the learning device 1 are realized by multiple information processing devices or circuits, these multiple information processing devices or circuits may be centrally located or distributed. For example, the information processing devices or circuits may be realized in a form in which each is connected via a communication network, such as a client-server system or a cloud computing system. Also, the functions of the learning device 1 may be provided in SaaS (Software as a Service) format.

[0022] The learning device according to Embodiment 1 establishes secure communication with information terminals connected to the networks of each organization and acquires local models using this secure communication. Therefore, according to Embodiment 1, a global model can be constructed even when the networks of multiple organizations are not constantly connected.

[0023] <Embodiment 2> Embodiment 2 is a specific example of Embodiment 1. Figure 2 is a schematic diagram showing the configuration of the learning system 100 according to Embodiment 2. The learning system 100 comprises information terminals 2a, 2b, and 2c, VPN devices 3a, 3b, and 3c, and a learning device 4. The learning device 4 is a specific example of the learning device 1 described above.

[0024] Organization A's network Na has information terminal 2a and VPN device 3a. Organization B's network Nb has information terminal 2b and VPN device 3b. Organization C's network Nc has information terminal 2c and VPN device 3c.

[0025] Datasets owned by organization A are stored on information terminal 2a. Datasets owned by organization B are stored on information terminal 2b. Datasets owned by organization C are stored on information terminal 2c.

[0026] Furthermore, information terminal 2a constructs a local model La that has been trained on the dataset owned by organization A. Information terminal 2b constructs a local model Lb that has been trained on the dataset owned by organization B. Information terminal 2c constructs a local model Lc that has been trained on the dataset owned by organization C. Information terminals 2a, 2b, and 2c update local models La, Lb, and Lc as the datasets are accumulated. When local models La, Lb, and Lc are not distinguished from each other, they may simply be referred to as local model L.

[0027] The number of organizations is not limited to three. There may be two organizations, or four or more. Each organization could be, for example, a pharmaceutical manufacturer or a chemical manufacturer. In this case, the dataset is a dataset of compounds. Each record in the compound dataset contains information such as the compound's structure and properties. The compound's structure is represented by a fixed-length bit string, where each bit in the bit string represents the presence or absence of a specific structure (e.g., a benzene ring). The property values ​​(e.g., tensile strength) may be values ​​obtained experimentally, or values ​​obtained through simulation or theoretical calculation. For example, data generated daily in the research and development work of organization A is stored in information terminal 2a. Of course, the dataset is not limited to a dataset of compounds; it can be a dataset of any object.

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

[0029] VPN devices 3a, 3b, and 3c are VPN servers or VPN-compatible routers. When VPN devices 3a, 3b, and 3c are not distinguished from each other, they may simply be referred to as VPN device 3. VPN device 3 may have the IP (Internet Protocol) address of learning device 4 pre-configured. The VPN may be an Internet VPN, an IP-VPN, or a wide-area Ethernet.

[0030] Figure 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, and an integration unit 43.

[0031] 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 the VPN device 3, which is 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 local model L, the communication establishment unit 41 terminates the VPN session. The learning device 4 may also be connected to the network N via a remote access VPN.

[0032] The timing at which the communication establishment unit 41 establishes secure communication, that is, the timing at which the learning device 4 establishes a VPN connection to network N, will be described later. This is because the timing may be related to the progress of processing in the integration unit 43, which will be described later. The timing at which secure communication is established with information terminal 2a, with information terminal 2b, and with information terminal 2c may be different from each other.

[0033] The acquisition unit 42 is a specific example of the acquisition unit 12 described above. The acquisition unit 42 acquires the local model L from the information terminal 2 after the learning device 4 has established a VPN connection to the network N.

[0034] The integration unit 43 is a specific example of the integration unit 13 described above. The integration unit 43 integrates the local models La, Lb, and Lc acquired by the acquisition unit 42. The integrated model is called the global model. The integration unit 43 may integrate the local models La, Lb, and Lc at predetermined intervals (e.g., once a day, once every few months). The global model is more powerful than the local models La, Lb, and Lc. The integration unit 43 may also perform a process to integrate the local models La, Lb, and Lc if they are updated.

[0035] The integration unit 43 may generate a global model by, for example, taking the arithmetic mean of the model parameters of local model La, local model Lb, and local model Lc. Note that the method of integrating the model parameters is not limited to the arithmetic mean.

[0036] After the integration unit 43 generates the global model, the learning device 4 distributes the global model to the information terminals 2a, 2b, and 2c. For example, after the process of generating the global model is completed, the learning device 4 may sequentially establish VPN connections to networks Na, Nb, and Nc and transmit the global model to the information terminals 2a, 2b, and 2c.

[0037] Furthermore, the learning device 4 may connect to network N via VPN in response to requests 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 will be able to utilize a high-performance global model that links datasets owned by multiple organizations.

[0038] The process of constructing multiple local models L and integrating them is also known as associative learning. Learning device 4 can be said to be performing associative learning.

[0039] The learning device 4 sequentially repeats the processes of establishing secure communication and acquiring the local model L. This allows the performance of the global model to be improved based on the datasets accumulated daily on each information terminal 2. The process of integrating multiple local models may be performed at any time.

[0040] Next, the timing of when the communication establishment unit 41 establishes secure communication will be explained. 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.

[0041] Furthermore, the communication establishment unit 41 may establish secure communication in response to the receipt of requests from each information terminal 2. For example, the information terminal 2 transmits the local model after newly training the local model L with a dataset exceeding a predetermined amount. The information terminal 2 may also transmit a request when the model parameters of the local model L converge during training with the dataset exceeding the predetermined amount.

[0042] When training a local model L with a single dataset, the dataset is divided into multiple batches, and the local model L is trained on each batch sequentially. This process of dividing the dataset into batches and training each batch is repeated a predetermined number of times. The predetermined number of repetitions is set so that the model parameters of the local model L converge. However, the predetermined number of repetitions must be set to a number that does not cause overfitting.

[0043] If the dataset is divided into five batches and training is repeated 10 times, the request may be sent when training is complete, i.e., when the 10th training is finished. Alternatively, the request may be sent when training is nearing completion, for example, when the 4th batch of the 10th training is completed.

[0044] 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 processing in the integration unit 43 is not a simple arithmetic mean, or if there are many organizations, the processing in the integration unit 43 may take a long time. It is efficient if the learning device 4 can start the next processing after the processing in the integration unit 43 is completed.

[0045] Furthermore, applying secure computation techniques may result in long processing times for the integration unit 43. It is known that the dataset used for training can be inferred by reverse engineering the local model L. Therefore, to improve the confidentiality of the local model L, it is desirable to perform secure computation when integrating the local model L. Secure computation is a technique that performs computational processing while the data remains encrypted, and secure computation techniques using multi-party computation (MPC) and homomorphic encryption are known.

[0046] Figure 4 is a flowchart showing the process for updating the local model L. Assume that the learning device 4 has stored the initial local model L (step S101).

[0047] 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.

[0048] 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 the local model L from the information terminal 2 (step S103). This updates the local model L, which is the basis for constructing the global model. After that, the communication establishment unit 41 terminates the secure communication.

[0049] In step S103, multiple local models L may be acquired. First, secure communication is established between the information terminal 2a and the learning device 4, the acquisition unit 42 acquires local model La from the information terminal 2a, and the communication establishment unit 41 terminates the secure communication. Then, secure communication is established between the information terminal 2b and the learning device 4, the acquisition unit 42 acquires local model Lb from the information terminal 2b, and the communication establishment unit 41 terminates the secure communication. Then, secure communication is established between the information terminal 2c and the learning device 4, the acquisition unit 42 acquires local model Lc from the information terminal 2c, and the communication establishment unit 41 terminates the secure communication. Of course, in step S103, local model L may be acquired from any of the information terminals 2a, 2b, and 2c. After acquiring (updating) local model L, the process returns to step S102. Note that the process of integrating multiple local models L may be performed at any time.

[0050] The learning device according to Embodiment 2 connects to each organization's network via VPN at an appropriate communication timing and acquires local models. This allows for the secure reception of local models and their updating at the appropriate time.

[0051] Secure communication is not limited to VPN communication. Secure communication may be any secure communication protocol (e.g., encryption protocol). The local model may also be sent from information terminal 2 to learning device 4 via email using a secure communication protocol (e.g., S / MIME).

[0052] <Modified form of Embodiment 2> A repository for storing datasets owned by each organization may be located in a location other than the information terminal 2 on which the local model L is built. In this case, the information terminal 2 may establish secure communication (e.g., SSL) with the repository as needed to obtain the datasets necessary for training. This ensures secure communication not only between the local model L and the global model, but also between the local model L and the repository.

[0053] <Embodiment 3> Embodiment 3 is a specific example of Embodiment 2. The learning device according to Embodiment 3 integrates the model parameters of the local model using secure computation. Figure 5 is a block diagram showing the configuration of the learning system 100a according to Embodiment 3. Comparing Figure 2 and Figure 5, a group of servers 5 has been added.

[0054] Server group 5 includes multiple secure computation servers 51. The number of secure computation servers 51 is not limited to three. However, it is preferable to have three or more secure computation servers 51 for efficient secure computation.

[0055] Server group 5 integrates local model La, local model Lb, and local model Lc, and transmits the result of the secure computation to learning device 4.

[0056] The integration unit 43 of the learning device 4 divides the model parameters of local model La into multiple (e.g., 3) shares and sends the multiple shares to multiple secure computing servers 51. The integration unit 43 divides the model parameters of local model Lb into multiple shares and sends the multiple shares to multiple secure computing servers 51. The integration unit 43 divides the model parameters of local model Lc into multiple shares and sends the multiple shares to multiple secure computing servers 51.

[0057] Each secure computation server 51 uses the received shares to perform secure computation to compute the global model. The shares do not reveal the local model, and computations using the shares can be considered secure computations. Multiple secure computation servers 51 may cooperate to perform multi-party computation (MPC). Since the computational complexity required to integrate the local model L is sufficiently small, the server group 5 is expected to be able to perform secure computations in a realistic amount of time.

[0058] Furthermore, all or part of the functions of the learning device 4 may be provided in the server group 5. Secure communication may be established between the server group 5 and the information terminal 2 by having multiple secure computation servers 51 connect to the network N via VPN. Model parameters of the local model L may be obtained by having multiple secure computation servers 51 receive multiple shares. Multiple secure computation servers 51 may integrate the model parameters of multiple local model L by performing secure computation.

[0059] Embodiment 3 also achieves the same effects as Embodiment 2. Furthermore, Embodiment 3 allows for the confidentiality of calculations for integrating the global model.

[0060] The program described above includes, when loaded into a computer, a set of instructions (or software code) for causing the computer to perform one or more of the functions described in the embodiments. The program may be stored in a non-temporary computer-readable medium or a physical storage medium. Examples, but not limited to, 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® disc or other optical disc storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage devices. The program may be transmitted over a temporary computer-readable medium or a communication medium. Examples, but not limited to, include temporary computer-readable medium or a communication medium that includes electrically, optically, acoustically, or otherwise propagating signals.

[0061] Although the present invention has been described above with reference to embodiments, the present invention is not limited thereto. Various modifications to the structure and details of the present invention can be made that are understandable to those skilled in the art within the scope of the invention.

[0062] Some or all of the above embodiments may also be described as follows, but are not limited to the following: (Note 1) A means for establishing secure communication with information terminals located on the network of each organization, An acquisition means that uses the aforementioned secure communication to acquire a local model trained on a dataset for each organization from the information terminal, Integration means for combining multiple acquired local models A learning device equipped with the following features. (Note 2) The communication establishment means establishes the secure communication in response to the receipt of a request from each information terminal. The aforementioned request is sent after the local model has been trained with a dataset exceeding a predetermined amount. The learning device described in Appendix 1. (Note 3) The aforementioned request is sent when the model parameters of the local model converge during new training on a dataset exceeding the predetermined amount. The learning device described in Appendix 2. (Note 4) The communication establishment means establishes the secure communication at a predetermined timing. The learning device described in Appendix 1. (Note 5) The communication establishment means establishes the next secure communication based on the progress of the process of integrating the multiple local models. The learning device described in Appendix 1. (Note 6) The integration means integrates the multiple local models using secure computation technology. The learning device described in Appendix 5. (Note 7) The communication establishment means establishes the secure communication by connecting the learning device to the network via VPN (Virtual Private Network). A learning device as described in any one of the items 1 to 6 of the appendix. (Note 8) Information terminals located on each organization's network, Learning device, A learning system equipped with, The learning device is Secure communication is established with the aforementioned information terminal, Using the aforementioned secure communication, a local model trained on organization-specific datasets is acquired from the information terminal. Integrate multiple acquired local models. Learning system. (Note 9) The learning device establishes the secure communication in response to receiving requests from each information terminal. The aforementioned request is sent after the local model has been newly trained with a dataset exceeding a predetermined amount. The learning system described in Appendix 8. (Note 10) Computers Secure communication is established between information terminals located on each organization's network. Using the aforementioned secure communication, a local model trained on organization-specific datasets is obtained from the information terminal. Integrate multiple acquired local models. Learning methods. (Note 11) On the computer, The process of establishing secure communication with information terminals located on each organization's network, Using the aforementioned secure communication, the process involves obtaining a local model trained on a dataset specific to each organization from the information terminal, The process of integrating multiple acquired local models A non-temporary, computer-readable medium that stores a program to execute. [Explanation of Symbols]

[0063] 1.4 Learning device 11, 41 Communication Establishment Unit 12, 42 Acquisition Department 13, 43 Integration Department 2, 2a, 2b, 2c Information terminals 3, 3a, 3b, 3c VPN device 100, 100a Learning System 5 Server Clusters 51 Secure Computing Server N, Na, Nb, Nc Network PN Public Network

Claims

1. A means for establishing secure communication with information terminals located on the network of each organization, An acquisition means that uses the aforementioned secure communication to acquire a local model trained on a dataset for each organization from the information terminal, Integration means for combining multiple acquired local models Equipped with, The communication establishment means establishes the secure communication in response to the receipt of a request from each information terminal. The aforementioned request is sent after the local model has been newly trained with a dataset exceeding a predetermined amount. Learning device.

2. The aforementioned request is sent when the model parameters of the local model converge in the new learning process. The learning device according to claim 1.

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

4. The communication establishment means establishes the next secure communication after the completion of the previous secure communication, based on the progress of the process of integrating the multiple local models. The learning device according to claim 1.

5. The integration means integrates the multiple local models using secure computation technology. The learning device according to claim 4.

6. The communication establishment means establishes the secure communication by connecting the learning device to the network via VPN (Virtual Private Network). A learning device according to any one of claims 1 to 5.

7. Information terminals located on each organization's network, Learning device, A learning system equipped with, The learning device is A communication establishment means for establishing secure communication with the aforementioned information terminal, An acquisition means that uses the aforementioned secure communication to acquire a local model trained on a dataset for each organization from the information terminal, An integration means for combining multiple acquired local models, Equipped with, The communication establishment means establishes the secure communication in response to the receipt of a request from each information terminal. The aforementioned request is sent after the local model has been newly trained with a dataset exceeding a predetermined amount. Learning system.

8. Computers To establish secure communication with information terminals located on each organization's network, Using the aforementioned secure communication, a local model trained on organization-specific datasets is obtained from the information terminal. Integrating multiple acquired local models Includes, Establishing the aforementioned secure communication means establishing the secure communication in response to the receipt of a request from each information terminal, The aforementioned request is sent after the local model has been newly trained with a dataset exceeding a predetermined amount. Learning methods.

9. On the computer, The process of establishing secure communication with information terminals located on each organization's network, Using the aforementioned secure communication, the process involves obtaining a local model trained on a dataset specific to each organization from the information terminal, The process of integrating multiple acquired local models Make it run, The process for establishing the secure communication involves establishing the secure communication in response to the receipt of a request from each information terminal. The aforementioned request is sent after the local model has been newly trained with a dataset exceeding a predetermined amount. program.

Images