Detecting overlapping communities via expanding core regions

A social circle usually has some cores. Inspired by this phenomenon, we consider that a community in a complex network is also formed around one or several core vertices, called core region. We define the core score of a vertex to reflect its ability to attract other vertices. Utilizing the core scores of vertices, we address how to find the core region of one community, and then we apply local expansion and optimization to detect communities based on these core regions. Besides detecting community structure, our method can detect some abnormal vertices that are the hubs of network. Experimental results based on artificial networks and real-world networks show that our method is more effective than some usual methods.