A Community Detection Algorithm Based on Correlation Analysis of Connection Pattern

Abstract

A large number of complex systems in the real world can be abstractly expressed as complex networks. However, the existing network in the real society contains some information of link pattern and there is some correlation between the vertices. Therefore, based on the idea of the correlation analysis between the link pattern of vertices, we propose a community detection algorithm based on correlation analysis of link pattern, named CCP algorithm. The algorithm firstly obtains the link pattern of the vertex, then calculates the correlation coefficient to obtain the correlation among the connection nodes and obtains the must-link and the cannot-link pairwise constraints. Secondly, expands the must-link and the cannot-link according to the transferability of the must-link. Then, according to the expanded cannot-link set cooperation seed node, the skeleton of the community structure is attracted to the must-link. Finally, the nodes that are not classified into the community is divided into corresponding communities by minimum spanning tree, and the final community structure is obtained. In order to verify the performance of the proposed method, experiments are carried out on the actual network data sets and synthetic network data sets. The experimental results show that the proposed algorithm can extract high quality community structures from the network.