A new algorithm for approximate pattern mining in multi-graph collections

作者：

Highlights：

• A new algorithm for directly mining FASs from multi-graph collection is introduced.

• An extension of DFS canonical form for dealing with multi-graphs is included.

• Improvements, in time for mining FASs from multi-graph collections, accordance to the reported in the literature were achieved.

摘要

•A new algorithm for directly mining FASs from multi-graph collection is introduced.•An extension of DFS canonical form for dealing with multi-graphs is included.•Improvements, in time for mining FASs from multi-graph collections, accordance to the reported in the literature were achieved.

论文关键词：Frequent approximate subgraphs,Pattern mining,Multi-graphs,Canonical forms,DFS code

论文评审过程：Received 22 January 2016, Revised 30 June 2016, Accepted 2 July 2016, Available online 4 July 2016, Version of Record 3 September 2016.

论文官网地址：https://doi.org/10.1016/j.knosys.2016.07.003