Research map / Probabilistic and scientific modeling / Molecules and proteins
Cluster-Wise Hierarchical Generative Model for Deep Amortized Clustering
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use cluster-wise generation with EAI instead of point-wise baseline clustering | CHiGac · MNIST | ACC: 0.9758 -> 0.9796 | Helped |
| Use cluster-wise generation with EAI instead of point-wise baseline clustering | CHiGac · STL-10 | DBI: 0.4728 -> 0.4364 | Helped |
| Use cluster-wise generation with EAI instead of point-wise baseline clustering | CHiGac · Reuters | DBI: 1.0613 -> 1.0582 | Helped |
| Use cluster-wise generation with EAI instead of point-wise baseline clustering | CHiGac · HHAR | ACC: 0.8904 -> 0.9076 | Helped |
| Replace AI with EAI (ablation) | CHiGac · MNIST | ACC: 0.9769 -> 0.9796 | Helped |
| Replace AI with EAI (ablation) | CHiGac · STL-10 | DBI: 0.4406 -> 0.4364 | Helped |
| Replace AI with EAI (ablation) | CHiGac · STL-10 | ACC: 0.9102 -> 0.9123 | Helped |
| Replace AI with Semi-AI (ablation) | CHiGac · MNIST | ACC: 0.9769 -> 0.9773 | Helped |
| Replace AI with IAI (ablation) | CHiGac · STL-10 | DBI: 0.4406 -> 0.4388 | Helped |
| Replace AI with SVI-AI (ablation) | CHiGac · MNIST | ACC: 0.9769 -> 0.9767 | No clear effect |
Closest papers by meaning
- Amortized Mixing Coupling Processes for Clustering (NeurIPS 2022 · similarity 0.87)
- Deep Amortized Relational Model with Group-Wise Hierarchical Generative Process (AAAI 2022 · similarity 0.87)
- From Logits to Hierarchies: Hierarchical Clustering made Simple (ICML 2025 · similarity 0.86)
- You Can Trust Your Clustering Model: A Parameter-free Self-Boosting Plug-in for Deep Clustering (NeurIPS 2025 · similarity 0.86)
- Hard Regularization to Prevent Deep Online Clustering Collapse without Data Augmentation (AAAI 2024 · similarity 0.84)
- Interactive Deep Clustering via Value Mining (NeurIPS 2024 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.