Community detection using boundary nodes in complex networks

We propose a new local community detection algorithm that finds communities by identifying borderlines between them using boundary nodes. Our method performs label propagation for community detection, where nodes decide their labels based on the largest “benefit score” exhibited by their immediate neighbors as an attractor to their communities. We try different metrics and find that using the number of common neighbors as benefit scores leads to better decisions for community structure. The proposed algorithm has a local approach and focuses only on boundary nodes during iterations of label propagation, which eliminates unnecessary steps and shortens the overall execution time. It preserves small communities as well as big ones and can outperform other algorithms in terms of the quality of the identified communities, especially when the community structure is subtle. The algorithm has a distributed nature and can be used on large networks in a parallel fashion.