Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Graph neural network training method and device

A neural network training and neural network technology, applied in the field of graph neural network training methods and devices, can solve the problems of time-consuming, low graph neural network training efficiency, etc., and achieve the effect of improving efficiency and reducing the amount of data

Pending Publication Date: 2021-05-28
BEIJING UNIV OF POSTS & TELECOMM
View PDF8 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, labeling graph data takes a lot of time, leading to low training efficiency of graph neural networks.

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 and device
  • Graph neural network training method and device
  • Graph neural network training method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0060] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art based on the present application belong to the protection scope of the present invention.

[0061] see figure 1 , figure 1 It is a schematic flowchart of a graph neural network training method provided by an embodiment of the present invention. The above method includes the following steps S101-S104.

[0062] Step S101: Obtain an unlabeled graph dataset and a first labeled graph dataset.

[0063] The graph dataset includes individual graph data. Wherein, the graph data includes each node data, and the node data is used to describe the nodes and r...

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 embodiment of the invention provides a graph neural network training method and device, and relates to the field of deep learning. The method comprises the steps of obtaining an unmarked graph data set and a first marked graph data set; taking the unmarked graph data set as a training sample, training a preset graph neural network model, and adjusting parameters of the graph neural network model to obtain a first graph neural network model; taking the first marked graph data set as a training sample, training the first graph neural network model, and adjusting parameters of the first graph neural network model to obtain a second graph neural network model; and taking the second marked graph data set of the to-be-applied scene of the graph neural network as a training sample, training a second graph neural network model, adjusting parameters of the second graph neural network model, and obtaining the graph neural network applied to the to-be-applied scene. When the scheme provided by the embodiment is applied to graph neural network training, the efficiency of graph neural network training is improved.

Description

technical field [0001] The invention relates to the technical field of deep learning, in particular to a graph neural network training method and device. Background technique [0002] In recent years, Graph Neural Networks (GNNs) have been more and more widely used in various fields such as social networks, knowledge graphs, and life sciences. As a kind of neural network, graph neural network can be used to classify objects. For example, graph neural network can classify objects such as molecular structure and literature data. It can be considered that the graph neural network corresponds to a graph, which contains multiple nodes, and each node can correspond to different objects. [0003] When training a graph neural network, a large amount of labeled graph data is usually used as a training sample to train a preset graph neural network model. Wherein, the graph data includes node data, and the node data is used to describe nodes and represent relationships between nodes....

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): G06N3/08G06N3/04G06N3/063
CPCG06N3/082G06N3/063G06N3/045Y02D10/00
Inventor 石川陆元福江训强
Owner BEIJING UNIV OF POSTS & TELECOMM
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com