Overlapping Community Detection with Graph Neural Networks

TL;DR

This paper introduces a GNN-based model for overlapping community detection in graphs, addressing a gap in existing methods that focus only on disjoint communities, and demonstrates its superior performance and robustness.

Contribution

The paper presents a novel GNN model specifically designed for overlapping community detection, outperforming existing baselines and confirming GNN's key role through ablation studies.

Findings

Outperforms existing baselines significantly in community recovery

Effective, scalable, and robust to hyperparameter variations

GNN is the key component driving the model's success

Abstract

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.