Research map / Label-efficient and robust learning / Recognition and long-tail
Label Distribution Learning by Optimal Transport
Peng Zhao, Zhi-Hua Zhou
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 |
|---|---|---|---|
| learn label correlations via optimal transport ground metric (LALOT) vs IIS-LLD | LDL · Yeast-alpha | Chebyshev: .0201 -> .0136 | Improved |
| LALOT vs best baseline | LDL · Yeast-spo | Chebyshev: .0636 -> .0603 | Improved |
| LALOT vs AA-KNN | LDL · Yeast-diau | Chebyshev: .0395 -> .0418 | Hurt |
| LALOT vs AA-KNN/AA-BP | LDL · Image | Chebyshev: .5130 -> .6850 | Hurt |
| LALOT vs AA-BP | LDL · Emotions | Cosine: .6979 -> .5513 | Hurt |
| LALOT vs IIS-LLD | LDL · Yeast-cold | Cosine: .9836 -> .9873 | Improved |
| LALOT vs IIS-LLD | LDL · Human Gene | Chebyshev: .0535 -> .0532 | No clear effect |
| learn ground metric jointly vs fixed metric (M=0 trivial) via kernel biased regularization (ablation) | LALOT · all datasets | loss | Improved |
| smaller entropic regularization lambda (Sinkhorn) in risk bound | LALOT · theory | risk bound | Hurt |
Closest papers by meaning
- Approximately Correct Label Distribution Learning (ICML 2025 · similarity 0.91)
- Divide and Conquer: Learning Label Distribution with Subtasks (ICML 2025 · similarity 0.89)
- Adaptive-Grained Label Distribution Learning (AAAI 2025 · similarity 0.89)
- Concentration Distribution Learning from Label Distributions (ICML 2025 · similarity 0.88)
- GLDL: Graph Label Distribution Learning (AAAI 2024 · similarity 0.88)
- LIMEFLDL: A Local Interpretable Model-Agnostic Explanations Approach for Label Distribution Learning (ICML 2025 · 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.
