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

Social network link prediction method based on attention neural network

A social network and neural network technology, applied in neural learning methods, biological neural network models, prediction, etc., can solve the problems of ignoring the redundancy of social network information and the dynamics of the structure, and the accuracy of the prediction results is poor, so as to shorten the chain. The time of road prediction, good structural information, and the effect of accurate social network link prediction results

Pending Publication Date: 2021-03-05
SHANXI UNIV +1
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to address the above-mentioned deficiencies in the prior art, and propose a social network link prediction method based on attention neural network, which is used to solve the problem that the existing link prediction method ignores the redundancy and structure of social network information The dynamic nature of the problem leads to poor prediction accuracy

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
  • Social network link prediction method based on attention neural network
  • Social network link prediction method based on attention neural network
  • Social network link prediction method based on attention neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] Attached below figure 1 , to further describe the specific steps of the present invention.

[0026] Step 1, construct the attention neural network.

[0027] Build a nine-layer attention neural network, its structure is: input layer, first fully connected layer, first regularization layer, second fully connected layer, second regularization layer, third fully connected layer, third Regularization layer, activation function layer, output layer.

[0028] The dimensions of the first to third fully connected layers are set to 256, 128, and 64 respectively, and the dimensions of the first to third regularization layers are set to 256, 128, and 64 respectively, and the activation function layer uses the Softmax function.

[0029] Step 2, generate a training set.

[0030] Select at least 1,000 network nodes from 30 types of node communities including network nodes, and all network nodes form at least 50,000 edges. The social network dataset is composed of node communities, n...

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 social network link prediction method based on an attention neural network. The method comprises the following steps: (1) constructing the attention neural network; (2) generating a social network training set; (3) sampling the training set; (4) training the attention neural network; and (5) performing link prediction on the social network sample. According to the method,the attention neural network is established and trained,so that the dynamic structure information of the social network can be better captured; and the attention is adopted, so that the method has relatively short processing time and relatively high link prediction accuracy when the social network with complex information is processed.

Description

technical field [0001] The invention belongs to the technical field of physics, and further relates to a method for predicting social network links based on an attention neural network in the technical field of computer systems of specific computer models. The present invention can divide the social network into time snapshot modeling processing to obtain snapshots, sample the snapshots to obtain open triples, and use the obtained open triples as the input of the neural network to perform social network link prediction tasks. Background technique [0002] As real-life non-Euclidean data, social networks can be naturally represented as network structures, which are usually used to represent a set of objects (i.e., nodes) and their relationships (i.e., edges). In conventional social relationship prediction, a large number of interpersonal visits or action trajectory investigations are usually required to determine whether there will be an intersection between two people in the...

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): G06Q10/04G06Q50/00G06N3/04G06N3/08
CPCG06Q10/04G06Q50/01G06N3/08G06N3/045
Inventor 解宇马芷璇张琛鱼滨
Owner SHANXI UNIV
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