Link prediction method based on graph neural network and capsule network

Abstract

The invention provides a link prediction method based on a graph neural network and a capsule network, and the method comprises the steps: carrying out the representation learning of a network through GNN, and generating corresponding node features; secondly, through a conversion block designed by the patent of the invention, converting the learned node features into an Edge feature map so that a link prediction problem is converted into a graph classification problem; thirdly, performing feature representation learning on the node pair feature graph by means of CapsNet, and capturing attributes of node pairs from different aspects for graph classification; and finally, performing wide evaluation on six networks without node attributes and three networks with node attributes, and analyzing the feasibility and effectiveness of the proposed GCCL method. Experimental results show that the GCCL method provided by the invention is obviously superior to the compared method not only in a network containing node attributes, but also in a network not containing node attributes, and the accuracy is averagely improved by about 20%. The reasonability and the effectiveness of the GCCL method in the link prediction task can be proved.

Description

technical field [0001] The invention relates to the technical field of network analysis, in particular to a link prediction method based on a graph neural network and a capsule network. Background technique [0002] In real life, a wide variety of complex systems can be modeled using complex networks, such as social, biological, information, and technological systems, where nodes in the network represent individuals or entities, and links or edges represent relationships between nodes or entities. relationship or interaction between them. Link prediction in the network refers to how to predict the possibility of connection between two nodes in the network that have not yet generated a connection edge through known network nodes and network structure and other information. This kind of prediction includes not only the prediction of unknown links, that is, links that actually exist in the network but have not been detected, but also the prediction of future links (links that ...

AI Technical Summary

Problems solved by technology

The method proposed by Kipf and Welling only uses the GNN method. Although it can learn high-quality node features from the graph, it does not fully consider how to apply the learned node feature information to the link prediction problem.

Images