Deep Modularity Networks with Diversity-Preserving Regularization
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911247194128384 |
|---|---|
| author | Salehi, Yasmin Giannacopoulos, Dennis |
| author_facet | Salehi, Yasmin Giannacopoulos, Dennis |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_13451 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Deep Modularity Networks with Diversity-Preserving Regularization Salehi, Yasmin Giannacopoulos, Dennis Machine Learning 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. |
| title | Deep Modularity Networks with Diversity-Preserving Regularization |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2501.13451 |