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

Independent decoupling convolutional neural network representation algorithm for graph data

A convolutional neural network and graph data technology, applied in the field of decoupling table learning algorithms, can solve the problem of ignoring the independence of latent factors, and achieve the effect of improving the quality of decoupling representation

Pending Publication Date: 2020-03-17
TIANJIN POLYTECHNIC UNIV
View PDF0 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, many people propose to use decoupled graph convolutional network to obtain latent factors of graph data, but this method only considers separate representation learning, while ignoring the independence between latent factors, so that the data is repeatedly expressed

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
  • Independent decoupling convolutional neural network representation algorithm for graph data
  • Independent decoupling convolutional neural network representation algorithm for graph data
  • Independent decoupling convolutional neural network representation algorithm for graph data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] The present invention will be further described in detail below in combination with specific embodiments. figure 1 The flowchart of the decoupled representation learning algorithm based on graph convolutional neural network of the present invention is given. Such as figure 1 As shown, a decoupling representation learning algorithm based on a graph convolutional neural network of the present invention includes:

[0020] 1. Obtain graph data as input, including feature vectors of nodes and their neighbors;

[0021] 2. Obtain neighbor nodes and map to the feature vector of the current node through different latent factors;

[0022] 3. Update the probability of connections between nodes through different latent factors and the representation of nodes on each latent factor in an iterative manner;

[0023] 4. Improve the independence between different latent factors by minimizing the Hilbert-Schmidt independence index;

[0024] 5. Output the representation after node sepa...

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 an independent decoupling convolutional neural network representation algorithm for graph data. A brand-new neural network structure decoupled by using independent factors is provided, decoupling representation learning is carried out by using a neighborhood routing mechanism, then independence of potential factor representation between nodes and neighbor nodes is enhanced by using an HSIC algorithm, and the independence is integrated into a convolutional neural network as a regularization item. Through the method, independence among potential factors of the nodes can beenhanced, and better graph node separation representation can be obtained. Through verification of different graph data, the method can be applied to three tasks including semi-supervised graph classification, graph clustering and graph visualization, and has good performance and obvious advantages.

Description

technical field [0001] The invention relates to a decoupling representation learning algorithm based on a graph convolutional neural network, belonging to the fields of machine learning, graph convolutional neural network, and graph representation learning. Background technique [0002] Graph convolutional neural network, as a typical deep learning technique on graph data, has attracted extensive attention. It extends the convolution operation of traditional data to graph data, and obtains the representation of nodes by learning the neighborhood information propagated by nodes. With this approach, various tasks such as node clustering, classification, and link prediction can be performed on the graph. At present, graph convolutional neural networks have been widely used in social networks, knowledge maps, protein interaction networks, world trade networks and other fields. [0003] Graph data are usually formed by a combination of multiple latent factors with highly comple...

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): G06F16/901G06F17/16G06N3/04
CPCG06F16/9024G06F17/16G06N3/045
Inventor 刘彦北李赫南肖志涛耿磊张芳吴俊王雯
Owner TIANJIN POLYTECHNIC 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