Research map / Label-efficient and robust learning / Recognition and long-tail
Label Distribution Learning by Exploiting Sample Correlations Locally
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 |
|---|---|---|---|
| exploit label correlations locally via clustered local correlation vector instead of globally (EDL) | LDL-SCL vs EDL · 8 yeast LDL datasets | KL divergence: alpha .0068 -> .0054 | Helped |
| add local correlation vector features (m clusters from 0) (ablation) | LDL-SCL · cold | six LDL measures | Helped |
| increase number of clusters m beyond 6 (ablation) | LDL-SCL · cold | six LDL measures | No clear effect |
| increase regularization lambda1/lambda2/lambda3 to large values (ablation) | LDL-SCL · cold | six LDL measures | Hurt |
| compare to best specialized baseline BFGS-LLD | LDL-SCL · diau | KL divergence: .0124 vs .0083 | Hurt |
Closest papers by meaning
- Divide and Conquer: Learning Label Distribution with Subtasks (ICML 2025 · similarity 0.90)
- Adaptive-Grained Label Distribution Learning (AAAI 2025 · similarity 0.90)
- Approximately Correct Label Distribution Learning (ICML 2025 · similarity 0.90)
- LIMEFLDL: A Local Interpretable Model-Agnostic Explanations Approach for Label Distribution Learning (ICML 2025 · similarity 0.89)
- Generative Calibration of Inaccurate Annotation for Label Distribution Learning (AAAI 2024 · similarity 0.89)
- Concentration Distribution Learning from Label Distributions (ICML 2025 · similarity 0.89)
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.