Community detection by using the extended modularity

Abstract

This article is about community detection algorithms in graphs. First a new method will be introduced, which is based on an extension [16] of the commonly used modularity [17, 18, 19, 20] and gives overlapping communities. We list and compare the results given by our new method and some other algorithms yileding either overlapping or non-overlapping communities. While the main use of the proposed algorithm is benchmarking, we also consider the possibility of hot starts, and some further extensions that considers the degree distribution of the graphs.