Community Detection in Feature-Rich Networks Using Gradient Descent Approach

The gradient descent has proven to be an effective optimization strategy. The current research proposes a novel clustering methodology using this strategy to recover communities in feature-rich networks. Our adoption of this strategy did not lead to promising results, and thus to improve them, we propose a special “refinement” mechanism, which culls out potentially misleading objects during the optimization. We validated and compared our proposed methods with three state-of-the-art algorithms over four real-world and 160 synthetic data sets. Our results proved that our proposed method is valid and in the majority of cases has a significant edge over the competitors.