Deep Modularity Networks with Diversity-Preserving Regularization
This work addresses feature-space diversity in graph clustering for researchers and practitioners, though it is incremental as it builds on existing DMoN methods.
The paper tackled the problem of graph clustering lacking feature-space diversity in Deep Modularity Networks by proposing DMoN-DPR with three novel regularization terms, resulting in significant improvements in label-based clustering metrics on benchmark datasets (p ≤ 0.05).
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.