Node-graph cross-layer graph matching method and system based on graph neural network

Abstract

The invention discloses a node-graph cross-layer graph matching system based on a graph neural network. The system comprises a graph node embedding vector encoding module, a node-graph cross-layer graph matching network module, a graph vector encoding module and a similarity calculation module. In addition, the invention further discloses a node-graph cross-layer graph matching method based on thegraph neural network. The method is based on a graph neural network. Learning cross-level interaction information of each node in one graph and the whole other graph in a fine-grained manner; according to the method, the embedded information of each node can be effectively updated, and a cross-layer graph matching system based on the method can be obtained by training based on an end-to-end mode,so that the similarity between any two graph data can be quickly and accurately calculated.

Description

technical field [0001] The invention relates to the field of graph data mining, in particular to a "node-graph" cross-layer graph matching method and system based on a graph neural network. Background technique [0002] With the continuous development of the big data era, graph data not only shows an exponential growth in quantity, but also is ubiquitous in the current big data environment. Graph data has a wide range of application scenarios, such as bioinformatics, chemical drugs, recommendation systems, social networks, static program analysis and other fields. [0003] The calculation of similarity between graph data is a basic problem in the application process of graph data, that is, given a specific graph data, it is necessary to search for one or several similar graph data from a database containing a large number of graph data. Therefore, in order to measure the similarity between graph data, two common metrics are currently proposed: graph edit distance and maximu...

AI Technical Summary

Problems solved by technology

Although the graph vectors of the two graph data contain the important information of each graph in this calculation method, it is impossible to perceive the finer-grained interaction information between the embedding vectors at different levels of the two graphs.

[0006] In general, the current methods of using neural networks to calculate the similarity of graph data have the following problems: 1) the low-level interaction information between graph data is not considered, and 2) the different levels (global and local) between two graphs are not considered at the same time. ) interaction information; 3) does not consider the cross-level interaction information between some nodes in one graph data and another graph as a whole

Images