Detecting overlapping communities in social networks using deep learning

Abstract

In network analysis, the community is considered as a group of nodes that is densely connected with respect to the rest of the network. Detecting the community structure is important in any network analysis task, especially for revealing patterns between specified nodes. There are various approaches in literature for community, overlapping or disjoint, detection in networks. In recent years, many researchers have concentrated on feature learning and network embedding methods for nodes clustering. These methods map the network into a lower-dimensional representation space. In this paper, we propose a model for learning graph representation using deep neural networks. In this method, a nonlinear embedding of the original graph is fed to stacked auto-encoders for learning the model. Then an overlapping clustering algorithm is employed to extract overlapping communities. The effectiveness of the proposed model is investigated by conducting experiments on standard benchmarks and real-world datasets of varying sizes. Empirical results exhibit that the presented method outperforms some popular community detection methods.