Network embedding learning method based on topology perception text representation

A learning method and representation technology, which can be used in biological neural network models, unstructured text data retrieval, text database browsing/visualization, etc. , the effect of performance improvement

Active Publication Date: 2021-07-13
SUN YAT SEN UNIV
View PDF11 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

These methods can achieve good results on small networks, but due to the high complexity of the algorithm, they are not suitable for large 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
  • Network embedding learning method based on topology perception text representation
  • Network embedding learning method based on topology perception text representation
  • Network embedding learning method based on topology perception text representation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] The accompanying drawings are for illustrative purposes only and cannot be construed as limiting the patent;

[0039] In order to better illustrate this embodiment, some parts in the drawings will be omitted, enlarged or reduced, and do not represent the size of the actual product;

[0040] For those skilled in the art, it is understandable that some well-known structures and descriptions thereof may be omitted in the drawings.

[0041] The technical solutions of the present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0042] Such as Figure 1-2 As shown, a network embedding learning method based on topology-aware text representation includes the following steps:

[0043] S1: Use the graph neural network to extract the local topology information of the nodes in the text network, and obtain the topology representation of all nodes;

[0044] S2: Input the topology representation of the node obtained in S1 to...

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 network embedding learning method based on topology perception text representation, which comprises the following steps of: adaptively generating a topology perception filter by using local topology structure information of a node, and learning the text representation so as to obtain the topology perception text representation. Topological structure information is more effectively fused into mining of text representation; besides, the method can be combined with an existing network embedding model based on context awareness, the application range is wider, the performance of link prediction and node classification tasks is improved, and the effectiveness of network node representation learned by the method is reflected.

Description

technical field [0001] The present invention relates to the field of network embedding methods, and more specifically, to a network embedding learning method based on topology-aware text representation. Background technique [0002] In the real world, data with a network structure is very common, for example, social networks based on Weibo, WeChat and other platforms, paper citation networks, etc. These networks often contain a large amount of information. Reasonable and effective mining of this information is very beneficial to the application of some downstream tasks, such as product recommendation in e-commerce systems and related paper recommendation. In today's era of explosive growth in the amount of information, these networks usually contain a large number of nodes and edges, and the scale is very large. Direct processing of the network requires a lot of time and storage space, and the calculation efficiency is very low. Therefore, it is of great significance to stu...

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): G06F16/901G06F16/906G06F16/34G06N3/04
CPCG06F16/9024G06F16/906G06F16/345G06N3/045Y02D30/70
Inventor 苏勤亮陈佳星
Owner SUN YAT SEN 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