OSMAC: Optimizing Subgraph Matching Algorithms with Community Structure

Abstract

Subgraph has gained increasing attention as it is an important query type on graphs. The efficiency of existing subgraph matching algorithms becomes unsatisfactory since graphs gradually get larger and more complex. This paper proposes an optimization method named OSMAC to accelerate subgraph matching algorithms with the community structure of data graphs. In essence, OSMAC changes the task of subgraph matching into dealing with all VC-mappings. An optimization method named community-structure-based boundary pruning is proposed to further improve the performance of OSMAC. It implements an efficient pruning method with the information of community structure and can reduce the search space. As a case study, we optimize TurboISO, one of the state-of-the-art subgraph matching algorithms, with OSMAC. The results of the experiments conducted on real-world data sets confirm that OSMAC is efficient and can improve the performance of subgraph matching algorithms significantly.