Link prediction method of graph attention network based on node similarity

Abstract

The invention discloses a link prediction method of a graph attention network based on node similarity, which comprises the following steps: firstly, constructing an undirected heterogeneous network model, preprocessing node data, and calculating a similarity matrix of the network; secondly, constructing a graph attention network model based on a node similarity index, and solving embedded representations of all nodes in the network; thirdly, carrying out negative sampling on information of existing edges, dividing all true edges and false edges into a training set and a test set, and using the training set and the test set in model training; and finally, inputting the embedded representations of the nodes learned through a graph attention method based on node similarity into a machine learning classifier in a series connection manner, and performing link prediction. According to the method, more related nodes are linked together through the node similarity index, so that the embedded representation learned by each node more fully represents the structural information of the network, and the embedded representation of the node obtains a better result in a downstream link prediction task.

Description

technical field [0001] The invention belongs to the field of graph neural networks, and in particular relates to a link prediction method of a graph attention network based on node similarity. Background technique [0002] In a complex network, the nodes in the network exist in a non-Euclidean space. Therefore, when representing the information of the nodes, in addition to considering the characteristic information of each node itself like the data in the Euclidean space, it is also necessary to consider the structural information between the nodes. . Excellent results can be achieved in downstream tasks such as node classification and link prediction only when the learned node embedding representation fully reflects all the feature information of nodes. Therefore, when learning the embedded representation of nodes in the network in the low-dimensional space, it is necessary to include all the information of each node as much as possible, including the node's own informatio...

AI Technical Summary

Problems solved by technology

This makes the embedded representation of the nodes learned by the graph attention network in the low-dimensional space unable to completely c

Images