Fusing data depth with complex networks: Community detection with prior information

A new nonparametric supervised algorithm is proposed for detecting multiple communities in complex networks using the Depth vs. Depth (DD(G)) classifier. The key idea behind the new clustering method is the notion of robust and data-driven data depth methodology that still remains new and unexplored in network sciences. The developed new DD(G)-method is inherently geometric and allows to simultaneously account for network communities and...