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

Graph classification method based on adaptive multi-channel cross graph convolutional network

A technology of convolutional network and classification method, applied in the field of graph classification based on adaptive multi-channel cross-graph convolutional network, which can solve the problems of FCN flexibility limitation and nodes being far apart.

Pending Publication Date: 2021-12-10
GUANGXI NORMAL UNIV
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, GCN has not fully exploited the potential of the network topology, and the flexibility of FCN is also limited.
Specifically, due to some sparsity and noise, the nodes of the same class may be far apart and nodes of different classes are directly connected, but GCN does not consider these phenomena

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 classification method based on adaptive multi-channel cross graph convolutional network
  • Graph classification method based on adaptive multi-channel cross graph convolutional network
  • Graph classification method based on adaptive multi-channel cross graph convolutional network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0044] refer to figure 1 , a graph classification method based on an adaptive multi-channel cross-graph convolutional network, comprising the following steps:

[0045] 1) Construct an initial graph based on the node feature matrix X:

[0046] Use G(X,A) to represent the graph, where the node feature matrix n represents the number of nodes in the graph, d represents the feature dimension of each node, is a symmetric adjacency matrix of n nodes, representing the topological structure between nodes, when A ij = 1, it means there is an edge between node i and node j, otherwise A ij = 0, indicating that there is no edge between node i and node j, use cosine similarity to obtain the similarity matrix Then select the first k similar node pairs for each node to set the edge, and finally get the adjacency matrix A f , and then get the input map in the feature space (X,A f ); similarly, for topological spaces, there is the original input graph Gt=(X t ,A t ), where X t =X,A ...

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 discloses a graph classification method based on an adaptive multi-channel cross graph convolutional network. The method comprises the following steps: 1) constructing an initial graph based on a node feature matrix X; (2) carrying out graph convolution operation on the input graph, (3) carrying out a cross network, (4) carrying out a graph convolution module, and (5) carrying out a full connection layer with an attention mechanism. The invention fully utilizes information in a space, eliminates the requirement of searching a plurality of multi-task network system structures on the basis of each task, and ensures the consistency of learning embedding.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence, in particular to a graph classification method based on an adaptive multi-channel cross graph convolutional network. Background technique [0002] Convolutional Neural Networks (CNN) are usually used for the representation and learning of Euclidean structured data. However, traditional convolutional neural networks cannot handle graph-structured data with irregular structures such as social networks and citation networks. Graph Convolutional Networks (GCN), as an extension of CNN from Euclidean structured data graphs to non-Euclidean structured data graphs, has received extensive attention and research from scholars because of its unique computing capabilities. Representation and learning from graph data in the fields of machine learning and computer vision. Contrary to previous deep learning architectures, GCNs have fewer parameters, can handle irregular data with non-Euclidean...

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): G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/22G06F18/24G06F18/214Y02D10/00
Inventor 李扬定胡泽辉苏子栋文国秋周鹏
Owner GUANGXI NORMAL UNIV
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

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