Dynamic network representation learning method for social network platform

A social network platform and dynamic network technology, applied in the field of dynamic network representation learning, to achieve good practicability and avoid gradient explosion and gradient disappearance.

Inactive Publication Date: 2020-07-28
NANJING UNIV OF POSTS & TELECOMM
View PDF3 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For the dynamic network representation learning method using traditional deep learning, since the network data belongs to non-Eucli...

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
  • Dynamic network representation learning method for social network platform
  • Dynamic network representation learning method for social network platform
  • Dynamic network representation learning method for social network platform

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] The present invention will be described in further detail below in conjunction with the accompanying drawings.

[0040] Such as figure 1 As shown, the present invention provides a dynamic network representation learning method for social network platforms, comprising the following steps:

[0041] 1. For the input network data, number the nodes that have appeared in it, and use the number as the id of the node itself. The number of each node is unique, and the set of nodes V={v 1 ,···,v n} and the set of edges

[0042] Read the original data, which is composed of the top 500 authors cited in DBLP papers and displayed in the form of (year, node_1, node_2) triples, where the field meanings are year, node 1 number and node 2 number respectively. Fetch the first 40 records as follows:

[0043]

[0044]

[0045]According to the read data, number all the nodes that have appeared in it, and use the number as the id of the node itself. The number of each node is uniq...

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 dynamic network representation learning method for a social network platform, and the method comprises the following steps: numbering all appearing nodes according to input original data; constructing a dynamic network according to the numbered node sequence and the original data; obtaining an adjacency matrix, a self-loop adjacency matrix and a corresponding degree matrix of the dynamic network; taking the obtained matrix as input and sending the matrix to a deep neural network model for learning; and training a neural network model, converting the original high-dimensional sparse matrix into a low-dimensional dense vector, and embedding time sequence information carried by the network into a new vector space. According to the method, feature extraction is carried out on the network data by using the graph convolutional neural network, and potential time sequence information in the network is captured in combination with the LSTM, so that feature informationand time sequence information contained in the high-dimensional network can be captured, and the method has good universality and can be applied to all related network analysis tasks.

Description

technical field [0001] The invention belongs to the technical field of representation learning, and in particular relates to a dynamic network representation learning method oriented to a social network platform. Background technique [0002] Network representation learning aims to represent the nodes in the network into a low-dimensional, real-valued, dense vector form, so that the obtained vector form can have the ability of representation and reasoning in the vector space. At present, the static network representation learning algorithm has been developed in the long run. However, most of the networks in the real world are dynamic rather than static, that is, the nodes or edges in the network will increase or decrease over time. . Simply applying the existing static network representation learning algorithm to each snapshot of the dynamic network usually results in unsatisfactory stability, flexibility, and efficiency. How to design the algorithm to make it more suitable...

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): G06Q50/00G06N3/04G06N3/08
CPCG06Q50/01G06N3/084G06N3/044G06N3/045
Inventor 徐小龙王扬
Owner NANJING UNIV OF POSTS & TELECOMM
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