Research map / Graph learning / Graph algorithms and clustering
Discretely-Refined Multi-view Clustering via Aligned Anchor Learning
Yuemeng Huang, Huibing Wang, Jinjia Peng, Lu Jiang, Qian Liu, Zetian Mi, Jiqing Zhang
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 missing module to the weakest two-module variant (full AVW+DF+GP vs variant 1) (ablation) | DRMC · BBC4 | ACC: 0.6336 -> 0.8832 | Improved |
| add the missing module to variant 2 (ablation) | DRMC · BBC4 | ACC: 0.7679 -> 0.8832 | Improved |
| add the missing module to variant 3 (ablation) | DRMC · BBC4 | ACC: 0.8642 -> 0.8832 | Improved |
| add the missing module to variant 1 (ablation) | DRMC · BDGP fea | ACC: 0.3932 -> 0.6148 | Improved |
| add the missing module to variant 2 (ablation) | DRMC · BDGP fea | ACC: 0.5104 -> 0.6148 | Improved |
| add the missing module to variant 3 (ablation) | DRMC · BDGP fea | ACC: 0.5664 -> 0.6148 | Improved |
| add the missing module to variant 1 (ablation) | DRMC · BDGP fea | NMI: 0.1711 -> 0.3769 | Improved |
| increase anchors from fewer than 5k to 5k (ablation) | DRMC · BBC4 and 3sources | ACC, NMI, Purity, F-score | Improved |
| vary lambda and rho over their ranges (ablation) | DRMC · MSRC v1, 3sources and one more dataset | ACC, NMI, Purity, F-score | No clear effect |
| use DRMC instead of second-best method on 3sources | best baseline · 3sources | ACC: 0.7396 -> 0.8343 | Improved |
| use DRMC instead of RCAGL-type baselines on Caltech101-20 Purity | best baseline (RCAGL) · Caltech101-20 | Purity: 0.8504 -> 0.7800 | Hurt |
| use DRMC on F-score for Caltech101-all | TLRLF4MVC · Caltech101-all | F-score: 0.2927 -> 0.1658 | Hurt |
Closest papers by meaning
- From Spectrum-free towards Baseline-view-free: Double-track Proximity Driven Multi-view Clustering (ICML 2025 · similarity 0.94)
- Towards Learnable Anchor for Deep Multi-View Clustering (AAAI 2025 · similarity 0.91)
- Learning Cluster-Wise Anchors for Multi-View Clustering (AAAI 2024 · similarity 0.91)
- Max-Mahalanobis Anchors Guidance for Multi-View Clustering (AAAI 2025 · similarity 0.91)
- Learn from View Correlation: An Anchor Enhancement Strategy for Multi-view Clustering (CVPR 2024 · similarity 0.91)
- Anchor Learning with Potential Cluster Constraints for Multi-view Clustering (AAAI 2025 · similarity 0.91)
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.
