The (un)supervised detection of overlapping communities as well as hubs and outliers via (bayesian) NMF

The detection of communities in various networks has been considered by many researchers. Moreover, it is preferable for a community detection method to detect hubs and outliers as well. This becomes even more interesting and challenging when taking the unsupervised assumption, that is, we do not assume the prior knowledge of the number K of communities. In this poster, we define a novel model to identify overlapping communities as well as hubs and outliers. When K is given, we propose a normalized symmetric nonnegative matrix factorization algorithm to learn the parameters of the model. Otherwise, we introduce a Bayesian symmetric nonnegative matrix factorization to learn the parameters of the model, while determining K. Our experiment indicate its superior performance on various networks.