基于图神经网络的子图匹配符号算法 后印本

Краткое изложение: Subgraph matching is a fundamental problem in graph data analysis and has important research significance. Aiming
at the problem of a large number of redundant searches in the subgraph matching algorithm, a subgraph matching
symbol algorithm based on graph neural network(SSMGNN) was proposed. The algorithm used the graph neural network
technology to aggregate the neighborhood information of nodes, and obtained the feature vector containing the local attributes
and structure of the graph, and used the vector as the filter condition to obtain the node candidate set C of the query
graph. In addition, optimizing the matching order and using symbolic ADD operations to construct each candidate region of
C in the data graph reduced redundant searches during subgraph enumeration verification. The experimental results show
that, compared with the VF3 algorithm, the algorithm effectively improve the solving efficiency of subgraph matching.