Research map / Label-efficient and robust learning / Recognition and long-tail
Preserving Ordinal Consensus: Towards Feature Selection for Unlabeled Data
Read the paperCheck 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 |
|---|---|---|---|
| add triplet-induced feature graph (alpha>0) vs none (ablation) | Ours · AT&T | NMI (%): 79.8 -> 86.2 | Helped |
| add triplet-induced feature graph vs none (ablation) | Ours · COIL20 | NMI (%): 74.7 -> 80.1 | Helped |
| add triplet-induced feature graph vs none (ablation) | Ours · LUNG | NMI (%): 52.3 -> 60.2 | Helped |
| triplet-induced instead of doublet-induced feature graph (ablation) | Ours · AT&T | NMI (%): 83.6 -> 86.2 | Helped |
| triplet-induced instead of doublet-induced feature graph (ablation) | Ours · Isolet1 | NMI (%): 78.9 -> 82.2 | Helped |
| add triplet graph regularization to UDFS (ablation) | UDFS · LUNG | NMI (%): 49.6 -> 51.7 | Helped |
| add triplet graph regularization to NDFS (ablation) | NDFS · USPS | NMI (%): 60.7 -> 63.5 | Helped |
| add triplet graph regularization to SOCFS (ablation) | SOCFS · UMIST | NMI (%): 49.4 -> 50.3 | Helped |
| add triplet graph regularization to RUFS (ablation) | RUFS · UMIST | NMI (%): 46.4 -> 47.2 | Helped |
| vary hyperparameters beta and alpha over 1e-6 to 1e6 (ablation) | Ours · USPS | NMI (%) | No clear effect |
| vary self-paced threshold s in [0.7, 0.9] (ablation) | Ours · benchmark datasets | NMI (%) | No clear effect |
Closest papers by meaning
- Consensus Guided Unsupervised Feature Selection (AAAI 2016 · similarity 0.90)
- Dependence Guided Unsupervised Feature Selection (AAAI 2018 · similarity 0.86)
- Parameter-Free Clustering via Self-Supervised Consensus Maximization (AAAI 2026 · similarity 0.85)
- Unsupervised Feature Selection on Networks: A Generative View (AAAI 2016 · similarity 0.85)
- Embedded Feature Selection on Graph-Based Multi-View Clustering (AAAI 2024 · similarity 0.84)
- Unknown-Aware Graph Regularization for Robust Semi-supervised Learning from Uncurated Data (AAAI 2024 · similarity 0.83)
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.