Research map / Learning theory and algorithms / Clustering
DMCAR: Disentangled Mixture-of-Experts with Context-Aware Routing for Multi-View Clustering
Baili Xiao, Ke Liang, Jiaqi Jin, Jun Wang, Yinbo Xu, Siwei Wang, En Zhu
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 D-MoE (ablation) | DMCAR-MVC · HW-6V | ACC (%): 89.52 -> 96.80 | Improved |
| add CAHR (ablation) | DMCAR-MVC · HW-6V | ACC (%): 92.17 -> 96.80 | Improved |
| add alignment loss (ablation) | DMCAR-MVC · HW-6V | ACC (%): 88.36 -> 96.80 | Improved |
| add disentanglement loss (ablation) | DMCAR-MVC · HW-6V | ACC (%): 94.65 -> 96.80 | Improved |
| add D-MoE (ablation) | DMCAR-MVC · BDGP | ACC (%): 91.87 -> 98.32 | Improved |
| add CAHR (ablation) | DMCAR-MVC · BDGP | ACC (%): 94.51 -> 98.32 | Improved |
| add alignment loss (ablation) | DMCAR-MVC · BDGP | ACC (%): 90.23 -> 98.32 | Improved |
| add disentanglement loss (ablation) | DMCAR-MVC · BDGP | ACC (%): 96.14 -> 98.32 | Improved |
| replace DMCAR-MVC by best baseline on ALOI-100 | MVC methods · ALOI-100 | ACC (%): 86.29 -> 80.36 | Hurt |
| use DMCAR-MVC instead of SDSNE | MVC methods · Cora | NMI (%): 34.35 -> 25.55 | Hurt |
| increase lambda2 (disentanglement weight) beyond 0.01 (ablation) | DMCAR-MVC · Cora/BDGP/CiteSeer | ACC (%) | Hurt |
| vary lambda1 (alignment weight) (ablation) | DMCAR-MVC · Cora/BDGP/CiteSeer | ACC (%) | No clear effect |
Closest papers by meaning
- Mixture of Experts as Representation Learner for Deep Multi-View Clustering (AAAI 2025 · similarity 0.93)
- EASEMVC:Efficient Dual Selection Mechanism for Deep Multi-View Clustering (CVPR 2025 · similarity 0.89)
- Information-Theoretic Disentangled Latent Modeling with Conditional Diffusion for Incomplete Multi-View Clustering (ICML 2026 · similarity 0.88)
- Deep Variational Incomplete Multi-View Clustering: Exploring Shared Clustering Structures (AAAI 2024 · similarity 0.88)
- Medusa: A Multi-Scale High-order Contrastive Dual-Diffusion Approach for Multi-View Clustering (CVPR 2025 · similarity 0.88)
- Robust Multi-view Clustering against Imperfect Information (NeurIPS 2026 · 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.
