Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Graph neural network training method and device

A neural network and training method technology, applied in the computer field, can solve problems such as computing resources and memory usage burden, achieve the effect of reducing memory usage and computing consumption, and ensuring accuracy

Pending Publication Date: 2020-12-15
ALIPAY (HANGZHOU) INFORMATION TECH CO LTD
View PDF0 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Usually, the graph neural network needs to use the information of its multi-order neighbors when determining the embedding expression of a node. However, as the order increases, the number of neighbors will increase exponentially, which will bring great impact on computing resources and memory usage. big burden

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

[0023] Multiple embodiments disclosed in this specification will be described below in conjunction with the accompanying drawings.

[0024] As mentioned earlier, a relational network graph can be abstracted to include a set of nodes and a set of edges, where nodes represent entities in the real world, and edges represent associations between entities. figure 1 A schematic diagram showing a relational network graph, where users are taken as nodes for example. As shown in the figure, users with associated relationships are connected by edges.

[0025] In recent years, the graph neural network model (or graph neural network, GNN network, GNN model) has developed rapidly, from the original graph convolutional neural network (Graph Convolutional Network, referred to as GCN) model to the graph neural network with attention mechanism Model, the effect of the model has been greatly improved. However, the introduction of attention mechanism also brings new challenges for graph sampli...

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 the method comprises the steps: obtaining a relation network graph, wherein each object node corresponds to a sampling probability set, and the sampling probability set comprises the sampling probability of each first-order neighbor node; performing multiple rounds of iterative updating on the graph neural networkon the basis of the relation network graph, wherein any round includes performing M-order neighbor node sampling by taking the first label node selected in the current round as a center, wherein anyi-order neighbor node sampling includes, for any first node in the sampled i-1th-order neighbor nodes, based on the current sampling probability set, sampling a plurality of neighbor nodes from a first-order neighbor node set, and classifying the neighbor nodes into an ith-order neighbor node; performing the current round of updating on the graph neural network based on the sampled neighbor nodeswithin the M order and the first service label carried by the first label node; and determining a plurality of training feedbacks corresponding to the plurality of neighbor nodes by using the updatedgraph neural network, and then updating the current sampling probability set of the first node.

Description

technical field [0001] The embodiments of this specification relate to the field of computer technology, and in particular to a training method and device for a graph neural network. Background technique [0002] The relationship network diagram is a description of the relationship between entities in the real world, and is currently widely used in various computer information processing. Generally, a relational network graph includes a set of nodes and a set of edges. Nodes represent entities in the real world, and edges represent connections between entities in the real world. For example, in a social network, people are entities, and relationships or links between people are edges. [0003] In many cases, it is hoped to analyze the topological characteristics of nodes, edges, etc. in the relational network graph, and extract effective information from them. The computing method to realize this kind of process is called graph computing. Typically, it is desired to repres...

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): G06Q50/00G06N3/04G06N3/08
CPCG06Q50/01G06N3/084G06N3/047G06N3/045
Inventor 吴郑伟刘子奇
Owner ALIPAY (HANGZHOU) INFORMATION TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products