Ap-FSM: A parallel algorithm for approximate frequent subgraph mining using Pregel

作者：

Highlights：

• Proposed an efficient parallel algorithm for approximate frequent subgraph mining.

• A two-step approach is developed for isomorphism check and pruning.

• We performed experiments on our in-house cluster over real large graph datasets.

• Ap-FSM outperforms the state-of-art subgraph mining algorithms.

摘要

•Proposed an efficient parallel algorithm for approximate frequent subgraph mining.•A two-step approach is developed for isomorphism check and pruning.•We performed experiments on our in-house cluster over real large graph datasets.•Ap-FSM outperforms the state-of-art subgraph mining algorithms.

论文关键词：Pattern mining,Frequent subgraphs,Graph isomorphism,Large graphs,Sampling

论文评审过程：Received 30 August 2017, Revised 6 April 2018, Accepted 7 April 2018, Available online 9 April 2018, Version of Record 25 April 2018.

论文官网地址：https://doi.org/10.1016/j.eswa.2018.04.010