# US 2024/0202492 A1 · Method and apparatus for training graph federated learning models using reinforcement learning-based data augmentation

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2024/0202492 A1
- Document ID: US20240202492A1
- Status: Published application
- Kind: A1
- Application number: 18/507,289
- Filed: 2023-11-13
- Published: 2024-06-20
- Earliest claimed: 2022-12-14
- Assignees: Research & Business Foundation Sungkyunkwan University
- Applicants: Research & Business Foundation SUNGKYUNKWAN UNIVERSITY
- Inventors: Soyoung LEE; Hogun PARK
- Web page: https://patentgrep.com/patent/US20240202492A1

## CPC

- G06N 3/04: Architecture, e.g. interconnection topology
- G06N 3/045: Combinations of networks
- G06N 3/084: Backpropagation, e.g. using gradient descent
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

The present disclosure relates to a method for training a neural network model. First screening data is determined by inputting first data not associated with at least one client into the neural network model to calculate similarity between the first data and second data associated with the at least one client. the neural network model is trained by performing backpropagation on the neural network model with reference to a reward determined based on a correlation between the first screening data and the second data.

## Claims

### Claim 1

A model training method comprising:
determining first screening data by inputting first data not associated with at least one client into a neural network model to calculate similarity between the first data and second data associated with the at least one client; and
training the neural network model by performing backpropagation on the neural network model with reference to a reward determined based on a correlation between the first screening data and the second data.

### Claim 2 (depends on 1)

The model training method of claim 1, wherein:
the neural network model includes at least one of a first model, a second model, and a third model,
the first model is a model that is trained on a distribution of the first data based on a learning process that includes outputting a first embedding vector for user-item interactions based on the first data,
the second model is a model that is trained on a distribution of the second data based on a learning process that includes outputting a second embedding vector for the user-item interactions based on the second data, and
the third model is a model that is trained on a distribution of the first screening data based on a learning process that includes outputting a third embedding vector for the user-item interactions based on the first screening data.

### Claim 3 (depends on 2)

The model training method of claim 2, wherein the determining of the first screening data includes:
calculating a probability that the first data and the second data are similar, with reference to the first embedding vector and the second embedding vector; and
determining a binary value through sampling based on the calculated probability.

### Claim 4 (depends on 2)

The model training method of claim 2, wherein the reward is determined based on calculation on a loss value for the second data and a loss value for the first screening data.

### Claim 5 (depends on 1)

The model training method of claim 1, further comprising:
in response to completion of a predetermined number of epochs, transmitting parameters of the trained neural network model to a server; and
receiving updated parameters of the neural network model from the server,
wherein the received parameters of the neural network model have been updated based on calculation on the parameters of the neural network model, which are received from each of a plurality of clients.

### Claim 6 (depends on 5)

The model training method of claim 5, further comprising: training the neural network model based on the received parameters of the neural network model.

### Claim 7

A model training apparatus comprising:
a memory having a model performance improvement program stored therein; and
a processor configured to load the model performance improvement program from the memory and execute the model performance improvement program,
wherein the processor determines the first screening data by inputting first data not associated with the at least one client into a neural network model and calculating a similarity between the first data and second data associated with the at least one client, and
wherein the processor trains the neural network model by perform backpropagation on the neural network model with reference to a reward determined based on a correlation between the first screening data and the second data.

### Claim 8 (depends on 7)

The model training apparatus of claim 7, wherein:
the neural network model includes at least one of a first model, a second model, and a third model,
the first model is a model that is trained on a distribution of the first data based on a learning process that includes outputting a first embedding vector for user-item interactions based on the first data,
the second model is a model that is trained on a distribution of the second data based on a learning process that includes outputting a second embedding vector for the user-item interactions based on the second data, and
the third model is a model that is trained on a distribution of the first screening data based on a learning process that includes outputting a third embedding vector for the user-item interactions based on the first screening data.

### Claim 9 (depends on 8)

The model training apparatus of claim 8, wherein the processor calculates a probability that the first data and the second data are similar, with reference to the first embedding vector and the second embedding vector, and determines a binary value through sampling based on the calculated probability.

### Claim 10 (depends on 8)

The model training apparatus of claim 8, wherein the reward is determined based on calculation on a loss value for the second data and a loss value for the first screening data.

### Claim 11 (depends on 7)

The model training apparatus of claim 7, wherein the processor, in response to completion of a predetermined number of epochs, transmits parameters of the trained neural network model to the server and receives updated parameters of the neural network model from the server,
wherein the received parameters of the neural network model have been updated based on calculation on the parameters of the neural network model, which are received from each of a plurality of clients.

### Claim 12 (depends on 11)

The model training apparatus of claim 11, wherein the processor further trains the neural network model based on the received parameters of the neural network model.

### Claim 13

A non-transitory computer-readable storage medium including computer executable instructions, wherein the instructions, when executed by a processor, cause the processor to perform a model training method comprising:
determining first screening data by inputting first data not associated with at least one client into a neural network model to calculate similarity between the first data and second data associated with the at least one client; and
training the neural network model by performing backpropagation on the neural network model with reference to a reward determined based on a correlation between the first screening data and the second data.

### Claim 14 (depends on 13)

The non-transitory computer-readable storage medium of claim 13, wherein:
the neural network model includes at least one of a first model, a second model, and a third model,
the first model is a model that is trained on a distribution of the first data based on a learning process that includes outputting a first embedding vector for user-item interactions based on the first data,
the second model is a model that is trained on a distribution of the second data based on a learning process that includes outputting a second embedding vector for the user-item interactions based on second data, and
the third model is a model that is trained on a distribution of the first screening data based on a learning process that includes outputting a third embedding vector for the user-item interactions based on the first screening data.

### Claim 15 (depends on 14)

The non-transitory computer-readable storage medium of claim 14, wherein the determining of the first screening data includes:
calculating a probability that the first data and the second data are similar, with reference to the first embedding vector and the second embedding vector; and
determining a binary value through sampling based on the calculated probability.

### Claim 16 (depends on 14)

The non-transitory computer-readable storage medium of claim 14, wherein the reward is determined based on calculation on a loss value for the second data and a loss value for the first screening data.

### Claim 17 (depends on 13)

The non-transitory computer-readable storage medium of claim 13, wherein the method further comprises:
in response to completion of a predetermined number of epochs, transmitting parameters of the trained neural network model to a server; and
receiving updated parameters of the neural network model from the server,
wherein the received parameters of the neural network model have been updated based on calculation on the parameters of the neural network model received from each of a plurality of clients.

### Claim 18 (depends on 17)

The non-transitory computer-readable storage medium of claim 17, wherein the method further comprises training the neural network model based on the received parameters of the neural network model.
