Network representation acquisition method based on deep learning

A deep learning and acquisition method technology, applied in neural learning methods, biological neural network models, neural architectures, etc., can solve problems such as the inability to represent representation vectors, and achieve the effect of accurate network representation vectors

Pending Publication Date: 2020-01-10
NORTHWESTERN POLYTECHNICAL UNIV
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] Aiming at the deficiencies in the prior art, the purpose of the present invention is to provide a network representation acquisition method based on deep learning to solve the technical problem that the prior art cannot express accurate representation vectors well

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
  • Network representation acquisition method based on deep learning
  • Network representation acquisition method based on deep learning
  • Network representation acquisition method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0021] This embodiment provides a network representation acquisition method based on deep learning, such as figure 1 shown, including the following steps:

[0022] Step 1, obtain a network containing node content, the network containing node content includes |V| nodes, |V|≠0;

[0023] Step 2, select one node from the |V| nodes as the current root node, perform a random walk on the network containing node content according to the current root node, and obtain N random walk sequences, where N is a positive integer, and each A random walk sequence includes a content sequence and a node identification sequence, where the nth content sequence and the nth node ID sequence Where T represents the total number of steps of random walk, n=1,2,...,N, represents the content vector of the qth node, Indicates the identification element of the qth node;

[0024] All |V| nodes in the network are used as root nodes to perform random walks, and a total of N random walk sequences are obt...

Embodiment 2

[0054] In this embodiment, a deep learning-based network representation acquisition method provided by the present invention is experimentally verified. The experiment uses the AAN dataset containing 17667 articles, 107879 reference relationships (edges of nodes in the network), and each The element is an extracted article, which contains the abstract and title of the original article. For each query article, in this embodiment, according to the ratio of 1:9, the nodes directly connected to it are randomly divided as hidden articles and seed articles. After removing 584 query articles and isolated articles, a new citation network is formed. There are 16,791 nodes and 88,617 edges in the network, and the Hash Trick method is used for dimension reduction processing, and the nodes are vectorized.

[0055] The method provided by the present invention and four classic algorithms are tested on the ANN data set, and the four classic algorithms are main_sttenHOPE, Node2Vec, SONESDNE a...

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 network representation acquisition method based on deep learning. The method comprises the following steps: 1, obtaining a network containing node content, the network containing the node content comprises |V| nodes, selecting any one node from the |V| nodes as a current root node, performing random walk on the network containing the node content according to the current root node to obtain a content sequence and a node identification sequence; and step 2, inputting the content sequence into a deep learning model based on an attention mechanism to obtain a predicted identification vector sequence, i.e., a network representation vector, and randomly walking the network containing the node content according to the current root node to obtain a content sequence and anode identification sequence. According to the method, the research result of the deep learning technology in the machine translation direction is applied to network representation learning, and the content and the structure of the network are fused from the perspective of machine translation to obtain an appropriate network representation vector.

Description

technical field [0001] The invention belongs to the field of machine learning, and in particular relates to a network representation acquisition method based on deep learning. Background technique [0002] In actual social life, many complex systems can be represented by a network structure. Nodes in the network represent data samples, and edges represent the relationship between nodes in the network. For example, in a social network composed of people connected to each other People represent nodes, and the relationship between people represents the edge of the network. In the citation network composed of the relationship between citations and citations between documents, the documents are nodes of the network, and the citation relationship between documents is the edge of the network. Sensors, In the Internet of Things formed by interrelated devices such as controllers, the devices represent the nodes of the network, and the connections between devices represent the edges o...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06N3/04G06N3/08
CPCG06N3/08G06N3/084G06N3/044G06N3/045
Inventor 杨黎斌王楠鑫蔡晓妍梅欣顾铭刘森
Owner NORTHWESTERN POLYTECHNICAL UNIV
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