Heterogeneous graph neural network representation method based on meta-path

A neural network and meta-path technology, applied in the field of heterogeneous graph neural network representation based on meta-path, can solve the problem of not including all, and achieve the effect of comprehensive node information, increasing breadth and richness

Inactive Publication Date: 2021-07-30
ANHUI AGRICULTURAL UNIVERSITY
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] (1), the neighbors of many nodes in the heterogeneous graph only contain individual types, not all

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
  • Heterogeneous graph neural network representation method based on meta-path
  • Heterogeneous graph neural network representation method based on meta-path
  • Heterogeneous graph neural network representation method based on meta-path

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0032] The present invention is a meta-path-based heterogeneous graph neural network representation method, which uses a restart random walk strategy to select all types of neighbors of the target node based on the meta-path, and uses LSTM to generate initial representations of nodes according to the information carried by the neighbor nodes. According to the different types of neighbor nodes, first use Bi-LSTM to aggregate the information of the same type of nodes to generate a type-based neighbor representation, and then use the attention mechanism according to the difference in the degree of influence of different types of nodes on the target node to generate a node representation based on a single element path . Finally, the attention mechanism is used between multiple meta-paths to generate the final node representation, and the generated represent...

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 heterogeneous graph neural network representation method based on meta-paths, which comprises the following steps of: 1, determining a plurality of meta-paths of a target node, sampling different types of neighbor nodes of the target node in each meta-path, and grouping according to the types; 2, performing feature extraction, node initial heterogeneous content coding and feature aggregation on the neighbor nodes obtained in the step 1 to obtain heterogeneous neighbor information; 3, respectively aggregating heterogeneous neighbor information of neighbor nodes generated in each meta path, and obtaining corresponding embedded representation; 4, combining and optimizing the embedded representation in each meta path based on the attention mechanism again, and generating a final embedded representation of the target node.

Description

technical field [0001] The invention relates to the field of heterogeneous information networks, in particular to a metapath-based heterogeneous graph neural network representation method. Background technique [0002] Representation learning in heterogeneous information networks is to find a meaningful vector representation for each node, which facilitates the implementation of downstream applications (such as link prediction, personalized recommendation). Various types of nodes in heterogeneous graphs contain a large amount of structural relationship information, such as the unstructured content of each node. Since when processing heterogeneous graphs, it is necessary to consider the heterogeneous attributes or content associated with each node, and to incorporate heterogeneous structural information composed of multiple types of nodes and edges, resulting in the progress of heterogeneous graph processing is not As easy as in isomorphic graphs. [0003] The existing hete...

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): G06N3/04G06N3/08G06K9/62G06F16/45G06F16/9535
CPCG06N3/08G06F16/45G06F16/9535G06N3/044G06N3/045G06F18/2155G06F18/24
Inventor 吴国栋范维成汪菁瑶涂立静李景霞
Owner ANHUI AGRICULTURAL UNIVERSITY
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