Detection of Similar Community in Large Network Based on Graph Edit Distance

Community structures in complex networks are pointers to many interesting properties which are otherwise obvious. Finding structural similarity within the networks is an open problem and many researchers are working in this direction. Graph Edit distance (GED) is a concept to extract the similarity / dissimilarity between two graphs. In this paper, we apply the concept of GED to discover similar communities in large networks. First, a large network is taken and it is represented as an attributed graph then communities are discovered using GED. The usefulness of the proposed method has been applied to Protein dataset and DBLP dataset and results are discussed.