Research map / Learning theory and algorithms / Clustering
Views Attention Fusion of Granular-ball Fuzzy Representations Split for Improved Multi-view Clustering
Shuaiyu Liu, Song Wu, Jie Xu, Yazhou Ren, Yang Yang, Xiaorong Pu, Guoying Wang
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 granular-ball fuzzy contrastive learning (GFCL) alone (ablation) | GFSAF (AE) · WebKB | accuracy (%): 88.64 -> 91.24 | Improved |
| add noise stripping loss (LNS) alone (ablation) | GFSAF (AE) · WebKB | accuracy (%): 88.64 -> 89.96 | Improved |
| add cross views attention (CVA) alone (ablation) | GFSAF (AE) · WebKB | accuracy (%): 88.64 -> 91.89 | Improved |
| add CVA to GFCL + LNS (ablation) | GFSAF (AE) · WebKB | accuracy (%): 94.03 -> 98.29 | Improved |
| add GFCL to LNS + CVA (ablation) | GFSAF (AE) · Caltech101-7 | accuracy (%): 84.37 -> 88.74 | Improved |
| add LNS to GFCL + CVA (ablation) | GFSAF (AE) · Prokaryotic | accuracy (%): 62.38 -> 63.89 | Improved |
| add all three modules vs none (ablation) | GFSAF (AE) · Prokaryotic | accuracy (%): 59.47 -> 63.89 | Improved |
| use fused representation instead of best single view (ablation) | GFSAF · Caltech101-7, NUSWIDE, Prokaryotic | accuracy (%): avg +3.97%, +25.98%, +11.92% over single view | Improved |
| raise lambda1 or lambda2 above 0.3 / 0.1 (ablation) | GFSAF · WebKB, NUSWIDE | accuracy (%) | Hurt |
| GFSAF vs best baselines on NUSWIDE | GFSAF (AE) · NUSWIDE | accuracy (%): 67.59 -> 62.64 | Hurt |
| GFSAF (AE) vs MGBCC | GFSAF (AE) · WebKB | accuracy (%): 90.02 -> 98.29 | Improved |
| GFSAF vs SoTA average | GFSAF (DAE) · 9 databases avg | accuracy (%): 72.85 -> 80.65 | Improved |
Closest papers by meaning
- Multi-view Granular-ball Contrastive Clustering (AAAI 2025 · similarity 0.88)
- Dual-stage Contrastive Learning-enhanced Multi-view Variational Clustering (ICML 2026 · similarity 0.87)
- Incomplete Contrastive Multi-View Clustering with High-Confidence Guiding (AAAI 2024 · similarity 0.86)
- EASEMVC:Efficient Dual Selection Mechanism for Deep Multi-View Clustering (CVPR 2025 · similarity 0.85)
- Enhanced then Progressive Fusion with View Graph for Multi-View Clustering (CVPR 2025 · similarity 0.85)
- Medusa: A Multi-Scale High-order Contrastive Dual-Diffusion Approach for Multi-View Clustering (CVPR 2025 · similarity 0.85)
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.
