Deep Modularity Networks with Diversity-Preserving Regularization

Yasmin Salehi, Dennis Giannacopoulos

Keywords: Graph Clustering, Graph Neural Networks, Graph Representation Learning

TL;DR: DMoN–DPR augments DMoN with centroid-distance (feature-space separation), assignment-dispersion variance, and a small-weight entropy term for gradual sharpening—delivering statistically significant NMI/F1 gains on feature-rich graphs.

Abstract: Graph clustering plays a crucial role in graph representation learning but often faces challenges in achieving feature-space diversity. While Deep Modularity Networks (DMoN) leverage modularity maximization and collapse regularization to ensure structural separation, they lack explicit mechanisms for feature-space separation, assignment dispersion, and assignment-confidence control. We address this limitation by proposing Deep Modularity Networks with Diversity-Preserving Regularization (DMoN–DPR), which introduces three novel regularization terms: distance-based for inter-cluster separation, variance-based for per-cluster assignment dispersion, and an assignment-entropy penalty with a small positive weight, encouraging more confident assignments gradually. Our method significantly enhances label-based clustering metrics on feature-rich benchmark datasets (paired two-tailed t-test, $p\leq0.05$), demonstrating the effectiveness of incorporating diversity-preserving regularizations in creating meaningful and interpretable clusters.

Submission Number: 32