Self-encoding neural network-based symbol diagram node classification method

A neural network and node classification technology, applied in character and pattern recognition, instruments, data processing applications, etc., can solve the problems of not considering the node relationship in the graph, not suitable for symbol graph learning, etc., to achieve less training data and computational complexity. low effect

Inactive Publication Date: 2018-07-31
TONGJI UNIV
View PDF0 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Since the existing non-symbolic graph representation learning does not consider the relationship of nodes in the graph, it is not suitable for symbolic graph learning

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
  • Self-encoding neural network-based symbol diagram node classification method
  • Self-encoding neural network-based symbol diagram node classification method
  • Self-encoding neural network-based symbol diagram node classification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0038] A symbolic graph node classification method based on self-encoding neural network, which is used to realize the unsupervised learning of symbolic graph model node representation vectors, and can rely on a small amount of labeled data to train classifiers to realize node type classification. The input of the method is a symbolic graph structure. The output is the category of the node. In this embodiment, user classification in a social network is taken as an example to describe implementation steps of the present invention in detail. Such as figure 1 As shown, the symbol graph node classification method based on self-encoder neural network includes the following steps:

[0039] S1. Construct an adjacency matrix based on the symbolic graph structure, specifically:

[0040] Given a symbolic graph containing N nodes, construct an N×N-dimensional matrix M, the value m of row i and j in M ij Indicates the connection status of the i-th and j-th nodes in the symbol graph, if...

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 relates to a self-encoding neural network-based symbol diagram node classification method. The method includes the following steps that: S1, an adjacency matrix is constructed on the basis of a symbol diagram structure; S2, the representation vectors of symbol diagram nodes are learned on the basis of a self-encoding model, so that the representation vectors of two nodes connected bya positive edge are adjacent to each other, and the representation vectors of two nodes connected by a negative edge are far away from each other; S3, on the basis of the obtained node representationvectors, a small number of nodes with type tags are adopted to train a classifier; and S4, the trained classifier is utilized to predict the type of an unknown node, a node type is outputted, and therefore, the node can be classified according to the node type. Compared with the prior art, the method of the invention has the advantages of low computational complexity, fewer required training data, no need for retraining new nodes and the like.

Description

technical field [0001] The present invention relates to a symbol graph node classification method, in particular to a symbol graph node classification method based on an autoencoder neural network. Background technique [0002] Symbolic graphs, as a special graph structure, widely exist in real society. For example, online social networks allow users to label other users as friends or enemies. Such social network user relationships constitute a symbolic graph model. At the same time, in a symbolic graph constructed based on a social network, a node represents a user, and the type of user is very important for social network analysis. For example, in the analysis of social network users, it is necessary to know which users are normal users or malicious users. Therefore, node classification of symbolic graphs is an important task in graph or social network analysis. [0003] Deep neural networks have achieved numerous breakthroughs in areas such as image, text, and speech rec...

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): G06K9/62G06K9/46G06K9/48G06Q50/00
CPCG06Q50/01G06V10/426G06V10/469G06F18/2411
Inventor 向阳袁书寒
Owner TONGJI UNIV
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