Overlapping Community Discovery Based on the Combination of Node Influence and beta-Connected Neighbors

摘要

We propose an overlapping community discovery algorithm that combines node influence and beta-connected neighbors for effectively detecting the overlapping community structure of complex networks. On the basis of the node influence and beta-connected neighbors, our method accurately detects the core node community and uses the improved similarity between the node and community to expand the core node community. Accordingly, the discovery and optimization of network overlapping communities are realized. Experiments on artificial and real-world networks demonstrate that our method significantly and consistently outperforms other comparison methods.