A High Resolution Clique-based Overlapping Community Detection Algorithm for Small-world Networks
In this paper we propose a clique-based high-resolution overlapping community detection algorithm. The hub percolation method is able to find a large number of highly overlapping communities. Using different hub-selection strategies and parametrization we are able to fine tune the resolution of the algorithm. We also propose a weighted hub-selection strategy, allowing the algorithm to handle weighted networks in a natural way, without additional filtering. We will evaluate our method on various benchmarks, and we will also demonstrate the usefulness of our algorithm on a real-life economic case-study.
This work is licensed under a Creative Commons Attribution 3.0 License.