Complex network link prediction method and system

A technology of complex network and prediction method, applied in the field of complex network link prediction method and system

Active Publication Date: 2021-08-10
宿州学院
View PDF3 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of the above problems, the present invention provides a complex network link prediction method and system, and proposes a new edge convolutional neural network to automatically learn edges (links) from complex 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
  • Complex network link prediction method and system
  • Complex network link prediction method and system
  • Complex network link prediction method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0070] A complex network link prediction method, using the user relationship network in the social network as an example, specifically expounds the composed network link prediction method based on edge-volumeted network, such as figure 1 As shown, using the network crawler to collect online social networks (such as Sina Weibo, Zhi) in users and their friends information, including the following steps: 1) Extract users and their social relationships, generate user social relational network G's neighboring matrix A n×n Where n represents the number of users, A ij = 1 Represents Node V i Vs. i There is a link between the existence, and A ij = 0 indicates node V i Vs. i There is no link; 2) According to the adjacent matrix A n×n And user basic information, use the Node2VEC algorithm to generate the property matrix X of the G node n×d Where n represents the number of nodes, D represents the representation vector dimension of each node, Node V i Description vector; 3) For node V i And ...

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 complex network link prediction method, which is based on edge convolution and comprises the following steps: designing edge convolution operation, and constructing an edge convolution layer; stacking an edge convolutional layer, constructing a graph neural network for learning link representation, and updating and learning edge connection representation; and extracting the representation of the associated node from the learned edge connection representation, and performing link prediction on the representation of the associated node. According to the invention, GNN end-to-end learning advantages and GNN essentially aggregate representation of neighbor nodes are fully utilized, a new edge convolutional neural network is proposed to learn edge embedding in a complex network, a link prediction problem is converted into a link classification problem, and deep fusion of a research result of link prediction and a deep learning technology on a graph is realized.

Description

Technical field [0001] The present invention belongs to the field of link prediction, and in particular, to a complex network link prediction method and system. Background technique [0002] As an emerging cross-discipline field, complex network science is not only a natural extension of a classic chart and random chart on mathematics, but also the innovation and development of system science and complexity. Link Prediction in complex networks As one of the core scientific issues across multiple disciplines, using the obtained information to predict the connection possibilities of the edges between nodes in the network. Link predictions include predictions that actually exist in the network but have not been detected, including predictions that do not exist in the network, but should exist or future possible future links. Link prediction as an abstraction of a wide range of universal problems, can be applied to any system in the form of an entity and its relationship into a netwo...

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): G06N3/04G06N3/08G06K9/62
CPCG06N3/08G06N3/048G06N3/045G06F18/24
Inventor 张志伟崔琳姜飞潘正高王超潘昊
Owner 宿州学院
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