Research map / Label-efficient and robust learning / Recognition and long-tail
Learning Generalized Label Distributions
Haitao Wu, Weiwei Li, Kun Yue, Xiuyi Jia
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 |
|---|---|---|---|
| represent labels as GLD instead of LD in SVR | SVR · artf | Hamming distance: .2338 -> .0143 | Improved |
| represent labels as GLD instead of LD in DF | DF · artf | Hamming distance: .2497 -> .0118 | Improved |
| represent labels as GLD instead of LD in BFGS | BFGS · artf | Hamming distance: .2532 -> .0670 | Improved |
| represent labels as GLD instead of LD in kNN | kNN · jura | Hamming distance: .4752 -> .1184 | Improved |
| represent labels as GLD instead of LD in Delta | Delta · jura | Hamming distance: .4720 -> .1102 | Improved |
| represent labels as GLD instead of LD in LRR | LRR · jura | Hamming distance: .4792 -> .1130 | Improved |
| represent labels as GLD instead of LD in SVR | SVR · wq | Hamming distance: .1844 -> .1649 | Improved |
| represent labels as GLD instead of LD in DF | DF · wq | Hamming distance: .2556 -> .1623 | Improved |
| represent labels as GLD instead of LD in kNN | kNN · wq | Hamming distance: .2317 -> .1644 | Improved |
| represent labels as GLD instead of LD in SVR | SVR · artf | OOD error rate: 12.70% -> 03.35% | Improved |
| represent labels as GLD instead of LD in DF | DF · artf | OOD error rate: 16.35% -> 02.45% | Improved |
| represent labels as GLD instead of LD in SVR | SVR · artf | Clark distance: .0307 -> .0307 | No clear effect |
Closest papers by meaning
- Predicting Label Distribution from Ternary Labels (NeurIPS 2024 · similarity 0.89)
- Adaptive-Grained Label Distribution Learning (AAAI 2025 · similarity 0.88)
- GLDL: Graph Label Distribution Learning (AAAI 2024 · similarity 0.88)
- Generalization Analysis for Multi-Label Learning (ICML 2024 · similarity 0.87)
- Divide and Conquer: Learning Label Distribution with Subtasks (ICML 2025 · similarity 0.87)
- LIMEFLDL: A Local Interpretable Model-Agnostic Explanations Approach for Label Distribution Learning (ICML 2025 · similarity 0.86)
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.
