Classification method based on hyper-graph transformation network

A classification method and neural network technology, applied in the field of deep neural network algorithm and node division, and graph mining, can solve problems such as inability to accurately classify, inability to deeply explore high-level node information in heterogeneous networks, etc., and achieve the effect of great application potential

Pending Publication Date: 2022-01-11
BEIJING UNIV OF TECH
View PDF0 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] In order to solve the problem that the existing technology cannot deeply explore the high-order node information of heterogeneous netwo

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
  • Classification method based on hyper-graph transformation network
  • Classification method based on hyper-graph transformation network
  • Classification method based on hyper-graph transformation network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0065] The experimental environment of this method is: Ubuntu18.04.5, GeForce RTX 3090 24GB, CUDA=11.2, python=3.8.3, pytorch=1.7.1. The training set and test set are divided, and the division ratio is 0.8. The main parameters are set as: Epoch=500, learn rate=0.0005, weight decay=0.001.

[0066] Obtain the data of the paper, and make the data set into two parts: node feature X and graph structure. The node feature is the ONE-HOT code of the thesis title, and the graph structure describes the topology of the node. Incidence Matrix Available Matrix Indicates that the vertical axis of H represents the node v, and the horizontal axis represents the hyperedge e, where N is the maximum number of nodes, and M is the maximum number of hyperedges. The element H(v,e) in the matrix is ​​defined as:

[0067]

[0068] calculate with Element D in the degree matrix of hypergraph node i v (i,i) is defined as:

[0069]

[0070] degree matrix D of hyperedge i e The inner elem...

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 classification method based on a hyper-graph transformation network, which is used for solving the problem that in the prior art, high-order semantic information in a heterogeneous network cannot be deeply explored, so that classification cannot be accurately carried out. According to the method, an end-to-end hyper-graph transform network (HGTN) is provided, the communication ability between hyper-edge amplification nodes is used for learning a high-order relation, and semantic information between different types of nodes is mined. Specifically, an attention mechanism is utilized to distribute weights for different types of hyper-graphs, high-order semantic information implied in an original heterogeneous hyper-graph is subjected to cascade learning, useful meta-paths are generated, node embedding features are learned in an end-to-end mode, and a node classification task is completed. The method has good accuracy and universality, and is suitable for node classification tasks of heterogeneous networks such as citation networks, media networks, social networks and the like.

Description

technical field [0001] The invention mainly relates to the fields of graph mining, deep neural network algorithm and node division, and in particular is a classification method based on a hypergraph transformation network. Background technique [0002] In recent years, the application of deep networks to non-Euclidean data processing tasks has attracted considerable attention. Among them, the emergence of the graph neural network has made a major breakthrough in the above tasks. ordinary Figure 1 An edge can connect two vertices, representing the relationship and message propagation between paired nodes. But for complex many-to-many relationships, simple graphs will lose a lot of useful high-level information. For example, papers are used as nodes, and the condition for connecting nodes is that they belong to the same author. For simple graphs, if two papers are authored by the same person, a connection relationship is established. However, the reality is not so simple:...

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
IPC IPC(8): G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/24
Inventor 张勇李孟燃李小勇张宇晴尹宝才
Owner BEIJING UNIV OF TECH
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
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap