A similarity-based community detection method with multiple prototype representation

摘要: Communities are of great importance for understanding graph structures in social networks. Some existing community detection algorithms use a single prototype to represent each group. In real applications, this may not adequately model the different types communities and hence limits clustering performance on To address problem, Similarity-based Multi-Prototype (SMP) approach is proposed paper. SMP, vertices carry various weights describe their degree representativeness. This mechanism enables be represented by more than one node. The centrality nodes used calculate weights, while similarity utilized guide us partitioning graph. Experimental results computer generated real-world networks clearly show that SMP performs well detecting communities. Moreover, method could provide richer information inner structure detected with help compared models.