Mining Set of Interested Communities with Limited Exemplar Nodes for Network Based Services

Abstract

Community detection provides invaluable help for various network based services, such as marketing and product recommendation. A specific service usually requires a set of interested communities rather than all communities in the network. In this paper, we address the cases where some exemplar nodes are provided in advance and the set of interested communities is mined for some specific services. Providing sufficient and suitable priori exemplars is not an easy task in most cases. With inadequate priori knowledge, most of recent community detection methods may fail to capture the requirements of a service. We describe the service requirements' essence by a so-called interested attribute subspace with large importance weights on some focus attributes, and study the problem of detecting the set of interested communities based on the guidance of the most limited exemplar information, i.e., two exemplar nodes from any potential interested community. An Interested Subspace and Community Mining (ISCM) method is proposed. In ISCM, a priori knowledge extension technique is designed at first by utilizing the neighborhood of the two exemplar nodes to get more exemplar nodes. Then the interested subspace is inferred from the extension. Finally the set of interested communities are located and mined by the guidance of the interested subspace. Experiments on synthetic datasets demonstrate the effectiveness and efficiency of our method and applications on real-world datasets show its application values for network based services.