Unlock instant, AI-driven research and patent intelligence for your innovation.

Graph neural network training method, client device and system

A neural network training, client device technology, applied in the field of graph neural network, can solve problems such as low work efficiency

Active Publication Date: 2020-02-04
NETEASE (HANGZHOU) NETWORK CO LTD
View PDF13 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a graph neural network training method, client device and system, to alleviate the technical problem of low work efficiency in the graph neural network training method in the prior art

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Graph neural network training method, client device and system
  • Graph neural network training method, client device and system
  • Graph neural network training method, client device and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0060] A graph neural network training method provided by an embodiment of the present invention is applied to a client device for graph neural network training, and the client device communicates with a server device for graph neural network training, such as figure 1 As shown, the method includes the following steps:

[0061] Step S11, in response to the user's environment creation operation, using the resources of the server device to create a graph training environment corresponding to the environment creation operation.

[0062] In the embodiment of the present invention, if the user wants to train the graph neural network to be trained, the user only needs to interact with the client device trained by the graph neural network. The above client device communicates with the server device trained by the graph neural network. The end device is used to provide the resources required for graph neural network training.

[0063] First, the user sends a request to the client dev...

Embodiment 2

[0107] The embodiment of the present invention also provides a client device for graph neural network training, the client device communicates with the server device for graph neural network training, and is mainly used to execute the graph neural network training provided by the first embodiment above method, the following specifically introduces the client device trained by the graph neural network provided by the embodiment of the present invention.

[0108] Figure 5 It is a functional block diagram of a client device for graph neural network training provided by an embodiment of the present invention, the client device includes: an environment creation module 10, a model creation module 20, a setting module 30, a training module 40, a determination module 50, in:

[0109] The environment creation module 10 is configured to respond to the user's environment creation operation and use the resources of the server device to create a graph training environment corresponding t...

Embodiment 3

[0137] The embodiment of the present invention also provides a graph neural network training system, such as Image 6 As shown, the graph neural network training system includes the client device 1 for graph neural network training in the first embodiment above, and also includes: a server device 2 for graph neural network training;

[0138] Wherein, the client device 1 communicates with the server device 2;

[0139] The server device 2 is used to provide resources required for graph neural network training.

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a graph neural network training method, client equipment and a graph neural network training system. The invention relates to the technical field of graph neural networks. The method is applied to client equipment for graph neural network training. The method comprises the following steps of firstly, responding an environment creation operation of a user to create a trainingenvironment of a graph neural network; creating a to-be-trained graph neural network in response to a model creation operation of a user; setting hyper-parameters of the to-be-trained graph neural network in response to a setting operation of a user; the training operation of the user is responded; training the to-be-trained graph neural network corresponding to different hyper-parameter combinations by utilizing the graph data training set; and finally, determining an optimal hyper-parameter combination corresponding to the graph data training set. On the basis of fully utilizing the graph data structure, the optimal hyper-parameter combination of the graph neural network to be trained for the graph data training set is quickly and automatically obtained, and the workload of user parameter adjustment is reduced, so that the technical problem of low working efficiency of a graph neural network training method in the prior art is relieved.

Description

technical field [0001] The present invention relates to the technical field of graph neural networks, in particular to a graph neural network training method, client device and system. Background technique [0002] Graph neural network GNN (Graph Neural Networks) is a method of processing graph data, mainly based on deep learning to process graph domain information, which can be processed according to the characteristics of graph data, because graph data is irregular (non-European) Yes, the graph neural network needs to regularize the graph data before learning or during the learning process, and process it into training samples of the same dimension on the basis of retaining the graph structure information as much as possible. The commonly used method is controlled by neighboring nodes, but Neighbor node control not only solves the data regularization problem, but also introduces new hyperparameters, such as the number of neighbor nodes and sorting rules, which makes the wo...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06N3/04G06N3/08
CPCG06N3/08G06N3/045
Inventor 朱钰森尚书胡志鹏
Owner NETEASE (HANGZHOU) NETWORK CO LTD