Circularly Searching Core Nodes Based Label Propagation Algorithm for Community Detection

Abstract

With the application of community detection in complex networks becoming more and more extensive, the application of more and more algorithms for community detection are proposed and improved. Among these algorithms, the label propagation algorithm is simple, easy to perform and its time complexity is linear, but it has a strong randomness. Small communities in the label propagation process are easy to be swallowed. Therefore, this paper proposes a method to improve the partition results of label propagation algorithm based on the pre-partition by circularly searching core nodes and assigning label for nodes according to similarity of nodes. First, the degree of each node of the network is calculated. We go through the whole network to find the nodes with the maximal degrees in the neighbors as the core nodes. Next, we assign the core nodes’ labels to their neighbors according to the similarity between them, which can reduce the randomness of the label propagation algorithm. Then, we arrange the nodes whose labels had not been changed as the new network and find the new core nodes. After that, we update the labels of neighbor nodes according to the similarity between them again until the end of the iteration, to complete the pre-partition. The approach of circularly searching for core nodes increases the diversity of the network partition and prevents the smaller potential communities being swallowed in the process of partition. Then, we implement the label propagation algorithm on the whole network after the pre-partition. Finally, we adopt a modified method based on the degree of membership determined by the bidirectional attraction of nodes and their neighbor communities. This method can reduce the possibility of the error in partition of few nodes. Experiments on artificial and real networks show that the proposed algorithm can accurately divide the network and get higher degree of modularity compared with five existing algorithms.