Ensemble-Based Algorithms to Detect Disjoint and Overlapping Communities in Networks

Given a set ${\cal AL}$ of community detection algorithms and a graph $G$ as inputs, we propose two ensemble methods $\mathtt{EnDisCO}$ and $\mathtt{MeDOC}$ that (respectively) identify disjoint and overlapping communities in $G$. $\mathtt{EnDisCO}$ transforms a graph into a latent feature space by leveraging multiple base solutions and discovers disjoint community structure. $\mathtt{MeDOC}$ groups similar base communities into a meta-community and detects both disjoint and overlapping community structures. Experiments are conducted at different scales on both synthetically generated networks as well as on several real-world networks for which the underlying ground-truth community structure is available. Our extensive experiments show that both algorithms outperform state-of-the-art non-ensemble algorithms by a significant margin. Moreover, we compare $\mathtt{EnDisCO}$ and $\mathtt{MeDOC}$ with a recent ensemble method for disjoint community detection and show that our approaches achieve superior performance. To the best of our knowledge, $\mathtt{MeDOC}$ is the first ensemble approach for overlapping community detection.