科研之友
微信
新浪微博
Facebook
分享链接
摘要
It is indicated that community structure is a common property in complex network. Detecting community structure can give a significant insight to structural and functional properties of complex network. In this paper, we propose an divisive algorithm to detect hierarchical community structure in complex network. By regarding nodes and communities as random variables, the algorithm uses correlation coefficient to calculate similarity of nodes, and then finds and removes set of local weak edges in complex network until the reasonable hierarchical communities are revealed. Experimental results in real-world and artificial networks demonstrate that the proposed algorithm is more accurate than existing mechanisms.
