Abstract
Identification and classification of overlap nodes in communities is an important topic in data mining. In this paper, a new graph-based (network-based) semi-supervised learning method is proposed. It is based on competition and cooperation among walking particles in the network to uncover overlap nodes, i.e., the algorithm can output continuous-valued output (soft labels), which corresponds to the levels of membership from the nodes to each of the communities. Computer simulations carried out for synthetic and real-world data sets provide a numeric quantification of the performance of the method.