DGCLUSTER: A Neural Framework for Attributed Graph Clustering via Modularity Maximization

• DOI: 10.1609/aaai.v38i10.28983
• Publication Date: 2024-03-25T10:51:21Z
• Authors: Aritra Bhowmick; Mert Kosan; Zexi Huang; Ambuj Singh; Sourav Medya
• Keywords: Modularity; Maximization

Graph clustering is a fundamental and challenging task in the field of graph mining where objective to group nodes into clusters taking consideration topology graph. It has several applications diverse domains spanning social network analysis, recommender systems, computer vision, bioinformatics. In this work, we propose novel method, DGCluster, which primarily optimizes modularity using neural networks scales linearly with size. Our method does not require number be specified as part input can also leverage availability auxiliary node level information. We extensively test DGCluster on real-world datasets varying sizes, across multiple popular cluster quality metrics. approach consistently outperforms state-of-the-art methods, demonstrating significant performance gains almost all settings.