作者: Yu Wu , Pengfei Chao , Weiqin Ying , Linlin He , Shiyun Chen
关键词:
摘要: Most of the existing community detection (CD) methods are designed primarily for unsigned networks containing only positive links. Therefore, it is significant to explore and design effective CD signed social (SNs) with both negative In this paper, we first utilize decomposable characteristic modularity Q establish a bi-objective model from SNs. Afterwards, conical area evolutionary algorithm based on (CAEAq-SN) developed solve efficiently. Furthermore, new tournament selection mechanism applied accelerate convergence Q. Experimental results benchmark synthetic SNs indicate that CAEAq-SN achieves not better structures in term NMI but also stronger robustness than MEAs-SN.