Study on Community Discovery Algorithm from the Perspection of Label Influence Propagation

Abstract

In order to better discover the overlapping communities, this paper proposes an overlapping community detection method (INFELPA) based on the influence of the label and the spread of the edge tags. We use the influence of the node to initialize the label on the edge and sort the edge's influence to avoid these random factors during the edge label updating process. In order to retain multiple communities we retain multiple labels on the edges and restore the completed edge tag to the node. The experimental results show that this algorithm has certain competitive advantages