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

Deep network characterization method of rich structural information

A technology of deep network and structural information, applied in the field of deep network representation with rich structural information, can solve the problems of noise data sensitivity, singleness, lack of node neighbor type selectivity, etc., to achieve the effect of improving the effect

Active Publication Date: 2018-11-16
UNIV OF SCI & TECH OF CHINA
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, the current existing algorithms are all designed from a single point of view, focusing on a certain aspect, such as the type of neighbor nodes, anti-interference, high-order information utilization, and nonlinear structural relationships. A comprehensive solution that considers
This leads to problems such as lack of selectivity of node neighbor types in existing algorithms, or sensitivity to noisy data.

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
  • Deep network characterization method of rich structural information
  • Deep network characterization method of rich structural information
  • Deep network characterization method of rich structural information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0017] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0018] Embodiments of the present invention provide a deep network characterization method with rich structural information, such as figure 1 As shown, it mainly includes the following steps:

[0019] Step 1. Obtain initial feature matrices of different orders of the network topology to capture the necessary network structure information.

[0020] In the embodiment of the present invention, when obtaining initial feature matrices of different orde...

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 deep network characterization method of rich structural information. Network characterization is performed from a comprehensive perspective by using rich multi-order structural information, for example, transition probability direction adjustment control parameters are imported for transition matrices of different orders, nonlinear dimension reduction processing is performed on the transition matrices of different orders by using stacking noise reduction autoencoder, and multi-order information is fused by using an attention mechanism to well improve the network characterization effect.

Description

technical field [0001] The invention relates to the fields of machine learning and network representation optimization, in particular to a deep network representation method with rich structural information. Background technique [0002] Network representation is a recent hot technology, because this technology can improve the predictive performance of neural networks, and can also be applied to a variety of other applications. Network representation is an important method to learn low-dimensional representations of network nodes, and its purpose is to capture and preserve effective structural information. Network representation in low-dimensional space can bring beneficial effects to a variety of network-related research, such as influence analysis, community discovery, node classification, economic decision support, etc. [0003] At present, among the many network representation methods that only use network topology information, the most effective and widely used methods...

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): H04L12/24
CPCH04L41/12H04L41/142H04L41/147
Inventor 乔立升陈恩红刘淇赵洪科
Owner UNIV OF SCI & TECH OF CHINA
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