Link prediction method of graph attention network based on node similarity
A link prediction and attention technology, applied in the field of graph neural network, can solve the problems of affecting the results, embedding representation cannot completely contain structural information, etc., and achieve the effect of strong expressive ability
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0028] The present invention will be further described in detail below in conjunction with the accompanying drawings.
[0029] The present invention proposes a link prediction method of graph attention network based on node similarity, such as figure 1 shown, including the following steps:
[0030] Step 1: Build an undirected heterogeneous network model, and preprocess the node data in the network to obtain the adjacency matrix of the network, and then use the node similarity index to calculate the similarity matrix of the network.
[0031] Prepare an undirected network data set: including files describing the link relationship between nodes, used to form the adjacency matrix of the network, and restore the structural characteristics of the complex network. In this embodiment, a common Cora data set is selected. This data set includes 2708 nodes and 5429 edges.
[0032] Data processing: Preprocess the data of the nodes representing the link relationship between the nodes in ...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
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