Overlapping Community Detection with Graph Neural Networks
It addresses overlapping community detection for graph analysis, an incremental improvement over existing disjoint methods.
The paper tackled overlapping community detection in graphs, a problem previously addressed mainly for disjoint communities, and proposed a simple GNN-based model that outperformed existing baselines by a large margin in community recovery.
Community detection is a fundamental problem in machine learning. While deep learning has shown great promise in many graphrelated tasks, developing neural models for community detection has received surprisingly little attention. The few existing approaches focus on detecting disjoint communities, even though communities in real graphs are well known to be overlapping. We address this shortcoming and propose a graph neural network (GNN) based model for overlapping community detection. Despite its simplicity, our model outperforms the existing baselines by a large margin in the task of community recovery. We establish through an extensive experimental evaluation that the proposed model is effective, scalable and robust to hyperparameter settings. We also perform an ablation study that confirms that GNN is the key ingredient to the power of the proposed model.