Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
4973051 | Journal of Industrial Information Integration | 2017 | 5 Pages |
The advances in graphs play an important role to understand interrelated data. Inside graphs, there are usually community structures where different portion of nodes are more tightly connected to form a group, and community detection has wide applications in marketing, management, health care, and education. Nowadays, many different methods are proposed to detect community structures from different perspective, but none of them can be a constant winner. Therefore, ensemble different methods can potentially improve the final result. In this paper, we present a framework for different methods to be combined for community detection, and experimental results show our framework can potentially generate a better result by different methods collectively than any single method.