Research map / Label-efficient and robust learning / Recognition and long-tail
A Structured Prediction Approach for Label Ranking
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 |
|---|---|---|---|
| Use Kemeny embedding with ridge regression rather than the strongest reported baseline | Label ranking · authorship | mean Kendall’s τ: 0.94±0.02 vs 0.94±0.02 | No clear effect |
| Use Kemeny embedding with ridge regression rather than the strongest reported baseline | Label ranking · glass | mean Kendall’s τ: 0.86±0.06 vs 0.89 | Hurt |
| Use Kemeny embedding with ridge regression rather than the strongest reported baseline | Label ranking · iris | mean Kendall’s τ: 0.97±0.05 vs 0.97 | No clear effect |
| Use Kemeny embedding with ridge regression rather than the strongest reported baseline | Label ranking · vehicle | mean Kendall’s τ: 0.89±0.03 vs 0.86 | Helped |
| Use Kemeny embedding with ridge regression rather than the strongest reported baseline | Label ranking · vowel | mean Kendall’s τ: 0.92±0.01 vs 0.88±0.02 | Helped |
| Use Kemeny embedding with kNN rather than the strongest reported baseline | Label ranking · wine | mean Kendall’s τ: 0.94±0.05 vs 0.95 | Hurt |
| Replace Kemeny with Hamming embedding (ablation) | kNN label-ranking model · vehicle | mean Kendall’s τ: 0.85±0.03 -> -0.21±0.04 | Hurt |
| Replace Kemeny with Hamming embedding (ablation) | ridge label-ranking model · wine | mean Kendall’s τ: 0.94±0.05 -> -0.36±0.03 | Hurt |
| Replace Kemeny with Lehmer embedding (ablation) | kNN label-ranking model · authorship | mean Kendall’s τ: 0.94±0.02 -> 0.93±0.02 | No clear effect |
| Replace Kemeny with Lehmer embedding (ablation) | ridge label-ranking model · iris | mean Kendall’s τ: 0.97±0.05 -> 0.97±0.03 | No clear effect |
| Use Hamming embedding rather than Kemeny or Lehmer when optimizing Kendall’s τ (ablation) | Label-ranking model · six benchmark datasets | mean Kendall’s τ | Mixed |
Closest papers by meaning
- Label Ranking through Nonparametric Regression (ICML 2022 · similarity 0.91)
- Improving Pairwise Ranking for Multi-Label Image Classification (CVPR 2017 · similarity 0.87)
- Linear Label Ranking with Bounded Noise (NeurIPS 2022 · similarity 0.87)
- Rethinking and Reweighting the Univariate Losses for Multi-Label Ranking: Consistency and Generalization (NeurIPS 2021 · similarity 0.86)
- ComRank: Ranking Loss for Multi-Label Complementary Label Learning (NeurIPS 2025 · similarity 0.86)
- Bipartite Ranking From Multiple Labels: On Loss Versus Label Aggregation (ICML 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.