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

A method of link prediction for complex networks

A link prediction and complex network technology, which is applied in the intersection of deep learning and network science, can solve problems such as the bottleneck of prediction results, achieve less human interference, and facilitate the processing of link prediction tasks

Active Publication Date: 2019-01-15
BEIJING NORMAL UNIVERSITY +1
View PDF3 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Traditional link prediction methods generally regard each part of the network as homogeneous, and do not distinguish the influence of each part on the target node, which is not in line with the actual situation, so there is a certain bottleneck in its prediction effect

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
  • A method of link prediction for complex networks
  • A method of link prediction for complex networks
  • A method of link prediction for complex networks

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] The present invention will be further elaborated below in conjunction with accompanying drawing and the concrete implementation process on Cora network:

[0034] The problem specifically solved by the present invention is the link prediction problem on the large-scale complex network, which is described as follows with the document citation network Cora data set:

[0035] The papers in this data set are modeled as nodes on the network, and the citation relationship between papers is modeled as the connection between nodes, regardless of the direction of the connection and the type of nodes. Finally, 2708 nodes can be obtained, and 5429 An unweighted and undirected network structure with connected edges, and predicting the connected edges in this network is very important for literature analysis in science. The present invention deletes part of the connected edges in the network as connected edges to be predicted, and uses undeleted connected edges as a training set.

...

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 method for link prediction of a complex network, an end-to-end link prediction model based on a graph attention network (GAT), and a batch training method of the model. The key of this model is to learn the attention distribution of network nodes to neighbors. The steps of model training and model prediction include: (1) inputting the topological structure of unweighted undirected homogeneous network; 2, sampling all nodes according to the topological structure of the training set, so as to batch the network; 3, inputting the batched training set into the model to train the model parameters; Step 4, inputting the point pair to be predicted, and the model outputs the probability of connecting edges between the point pairs. The model of the invention has the characteristics of end-to-end. The batch training method makes the model suitable for large-scale complex networks.

Description

technical field [0001] The invention relates to the cross field of deep learning and network science, in particular to an end-to-end complex network link prediction model and its batch training method. The model uses the attention mechanism, combined with the network topology, to represent the network edges. The method of batch training enables the network to handle the link prediction problem of large-scale networks. technical background [0002] Large-scale complex networks are ubiquitous in the real world, such as the World Wide Web, aviation networks, online social networks, and protein networks, among others. Understanding, predicting and controlling these complex networks is an increasingly urgent human need. The study of complex networks is an interdisciplinary field, that is, theoretical research from the perspective of mathematics and physics, as well as algorithm research combined with computer technology, is one of the current research hotspots in the field of s...

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): G06Q10/04G06Q50/00G16B5/00
CPCG06Q10/04G06Q50/01
Inventor 谷伟伟高飞张江
Owner BEIJING NORMAL UNIVERSITY
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