Graph embedding method and device, and storage medium

Abstract

The invention provides a graph embedding method and device, and a storage medium, and the method comprises the steps: reading graph structure data and node feature values in a target graph, and building a graph structure model; regarding each node in the graph structure model as a target node, and sampling a first-order neighbor node of each target node according to the non-uniform neighbor node sampling function to obtain a first-order neighborhood of each target node; constructing second-order neighborhoods of the target nodes according to the first-order neighborhoods of the target nodes, aggregating the second-order neighborhoods to the first-order neighborhoods corresponding to the target nodes, and inputting the aggregated features of the second-order neighborhoods into the fully-connected neural network to obtain new features of the first-order neighborhoods of the target nodes; and aggregating the new features to the corresponding target nodes, and inputting the aggregated newfeatures of the first-order neighborhood into the fully-connected neural network to obtain output features of the target nodes. The neighborhood can be flexibly and effectively constructed for each node in the graph, and feature aggregation can be rapidly carried out, so that the graph embedding effect based on the graph neural network is improved.

Description

technical field [0001] The present invention mainly relates to the field of graph embedding technology processing, in particular to a graph embedding method, device and storage medium. Background technique [0002] Graph embedding is also called network embedding and network representation learning. Its purpose is to project each node in the graph into a low-dimensional vector space, that is, to learn effective representations or codes for graph-structured data. These representations or codes are the "embeddings" of graphs. ". There are various methods of graph embedding, among which graph neural network-based methods have slowly emerged in recent years. [0003] The embedding of a graph can be understood as many nodes in the embedding space, and tasks such as community discovery and intelligent recommendation can be realized by classifying and predicting these nodes. Graph embedding technology has greatly improved the effect of many data mining tasks in the complex networ...

AI Technical Summary

Problems solved by technology

[0004] At present, graph embedding methods often use a uniform sampling function to construct neighborhoods for each node, that is, randomly select some nodes from the neighbor nodes of each node. The difference exists in nature, which is not conducive to the generation of node embeddings

Images