Empirical evaluation of applying ensemble ranking to ego-centered communities identification in complex networks

In this paper we propose a new approach for efficiently identifying ego-centered communities in complex networks. Most existing approaches are based on applying a greedy optimisation process guided by a given objective function. Different objective functions has been proposed in the scientific literature, each capturing some specific feature of desired communities. In this work, we propose to apply ensemble ranking approaches in order to combine different objective functions. Preliminary Results obtained from experiments on benchmark networks argue for the relevancy of our approach.