An ensemble based on a bi-objective evolutionary spectral algorithm for graph clustering

作者：

Highlights：

• Approaching the conflicting terms of modularity by bi-objective heuristic MOSpecG.

• SpecG-EC to obtain consensus clusterings among the partitions found by MOSpecG.

• Partitions found by MOSpecG and SpecG-EC may control the resolution limit.

• SpecG-EC outperformed a bi-objective algorithm found in the literature.

摘要

•Approaching the conflicting terms of modularity by bi-objective heuristic MOSpecG.•SpecG-EC to obtain consensus clusterings among the partitions found by MOSpecG.•Partitions found by MOSpecG and SpecG-EC may control the resolution limit.•SpecG-EC outperformed a bi-objective algorithm found in the literature.

论文关键词：Graph clustering,Community detection,Evolutionary heuristic,Multi-objective optimization,Modularity maximization,Spectral decomposition

论文评审过程：Received 16 October 2018, Revised 21 May 2019, Accepted 31 August 2019, Available online 2 September 2019, Version of Record 13 September 2019.

论文官网地址：https://doi.org/10.1016/j.eswa.2019.112911