Supercharge Your Innovation With Domain-Expert AI Agents!

Graph kernel-based deep network embedded learning model

A technology of deep networks and learning methods, applied in neural learning methods, machine learning, biological neural network models, etc., can solve problems such as sparse social networks

Inactive Publication Date: 2020-07-28
NAT COMP NETWORK & INFORMATION SECURITY MANAGEMENT CENT
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] But real social networks are often sparse, where most of the nodes have only a few links pointing to other nodes

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 kernel-based deep network embedded learning model
  • Graph kernel-based deep network embedded learning model
  • Graph kernel-based deep network embedded learning model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] The method of the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments of the present invention.

[0043] Such as figure 1 As shown, the present invention is a graph kernel-based deep network embedding learning model, figure 2 An example of the present invention is given. The specific implementation steps are as follows:

[0044] Step 1: Construct the substructure set of nodes

[0045] The complete topology and semantic information of nodes are often preserved in certain substructures. For example, the connection between a node and its neighbors forms the neighborhood substructure of the node, and nodes often belong to certain communities to form the community substructure, etc. Build a set of substructures for each node, denoted as G v ={G i}, where G i is a substructure belonging to node v. For the neighborhood substructure, the breadth-first sampling method is used to collect all the neighb...

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 graph kernel-based deep network embedded learning model, which comprises five parts of constructing a substructure set of nodes, generating feature vectors of substructures,approximating the feature vectors in a plurality of reconstructed kernel Hilbert spaces, designing a graph kernel-based deep convolution model, and proposing an optimization method for mining potential community information. According to the method, the technologies of social network analysis, graph algorithm analysis, machine learning and the like are comprehensively utilized, high-quality representation vectors are generated for the nodes of the network, then research of other applications can be carried out based on the vectors, and a key basis is provided for further research of the characteristics of the social network and mining of related information.

Description

technical field [0001] The invention relates to a graph kernel-based deep network embedding learning method, which generates representation vectors for network nodes, and then conducts research on other applications based on the vectors, and is suitable for social network analysis, etc.; it belongs to data mining, machine learning, and social networks and graph algorithm research field. Background technique [0002] With the popularity of social networks, researchers began to use machine learning algorithms to mine valuable information from social network multimodal data, for example, using the attention relationship between users (structural data) and the attribute information of users themselves (micro Blog text, personal attributes, that is, content data), model user interests, and then classify, cluster and recommend users. A very important technique in this regard is Network Embedding, whose purpose is to learn a low-dimensional, continuous, dense representation vector...

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): G06N20/00G06N3/04G06N3/08G06Q50/00
CPCG06N20/00G06N3/08G06Q50/01G06N3/045
Inventor 王禄恒赵志云孙小宁葛自发赵忠华万欣欣李欣孙立远袁忠怡张冰付培国王晴张小明
Owner NAT COMP NETWORK & INFORMATION SECURITY MANAGEMENT CENT
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com