Research map / Image generation / Autoregressive and latent generation
Information-Theoretic Disentangled Latent Modeling with Conditional Diffusion for Incomplete Multi-View Clustering
Wenlan Chen, Lu Gao, Daoyuan Wang, Cheng Liang, Fei Guo
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| add the mutual-information disentanglement constraint (ablation) | IDCD · benchmark datasets (missing rate 0.1) | clustering ACC/NMI/ARI | Improved |
| use conditional diffusion instead of an MLP for view generation (ablation) | IDCD · benchmark datasets (missing rate 0.1) | clustering ACC/NMI/ARI | Improved |
| use Mixture of Wasserstein Barycenters instead of mean aggregation (ablation) | IDCD · benchmark datasets (missing rate 0.1) | clustering ACC/NMI/ARI | Improved |
| use Mixture of Wasserstein Barycenters instead of product-of-experts (ablation) | IDCD · benchmark datasets (missing rate 0.1) | clustering ACC/NMI/ARI | Improved |
| IDCD instead of DCG for missing-view reconstruction | IDCD · CARL CLASSIC view | PSNR: 5.75 -> 14.58 | Improved |
| IDCD instead of BURG for missing-view reconstruction | IDCD · CARL THERMAL view | PSNR: 15.70 -> 17.09 | Improved |
| IDCD instead of BURG for missing-view reconstruction | IDCD · CARL INFRARED view | RMSE: 0.21 -> 0.19 | Improved |
| IDCD instead of DCG on clustering | IDCD · CUB and HandWritten | ACC/NMI/ARI: up to approximately 6% in ACC, 2% in NMI, and 4% in ARI | Improved |
| increase missing rate from 0.1 to 0.7 | IDCD · HandWritten | ACC: 97.17 -> 92.73 | Hurt |
| increase missing rate from 0.1 to 0.7 | IDCD · CUB | ACC: 82.00 -> 71.83 | Hurt |
| vary alpha, beta, gamma, diffusion step T and mixture components K | IDCD · benchmark datasets | clustering metrics | No clear effect |
| recover missing views before clustering | IDCD · HandWritten (missing rate 0.5) | t-SNE cluster structure | Improved |
Closest papers by meaning
- Adaptive Feature Imputation with Latent Graph for Deep Incomplete Multi-View Clustering (AAAI 2024 · similarity 0.91)
- Deep Variational Incomplete Multi-View Clustering: Exploring Shared Clustering Structures (AAAI 2024 · similarity 0.91)
- Incomplete Contrastive Multi-View Clustering with High-Confidence Guiding (AAAI 2024 · similarity 0.90)
- Incomplete Multi-view Clustering via Diffusion Contrastive Generation (AAAI 2025 · similarity 0.90)
- Robust Multi-view Clustering against Imperfect Information (NeurIPS 2026 · similarity 0.89)
- Incomplete Multi-view Clustering via Hierarchical Semantic Alignment and Cooperative Completion (NeurIPS 2025 · similarity 0.88)
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.
