摘要
Information mining from complex networks by identifying communities is an important problem in a number of research fields, including the social sciences, biology, physics and medicine. First, two concepts are introduced, Attracting Degree and Recommending Degree. Second, a graph clustering method, referred to as AR-Cluster, is presented for detecting community structures in complex networks. Third, a novel collaborative similarity measure is adopted to calculate node similarities. In the AR-Cluster method, vertices are grouped together based on calculated similarity under a-K-Medoids framework. Extensive experimental results on two real datasets show the effectiveness of AR-Cluster.
- 出版日期2017-3-1
- 单位西安理工大学