Research map / Label-efficient and robust learning / Recognition and long-tail
Towards Better IncomLDL: We Are Unaware of Hidden Labels in Advance
Jiecheng Jiang, Jiawei Tang, Jiahao Jiang, Hui Liu, Junhui Hou, Yuheng 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 |
|---|---|---|---|
| add proportional constraint (ablation) | HidLDL · Emo recovery (50% missing) | Clark: 1.679 -> 1.249 | Improved |
| add proportional constraint (ablation) | HidLDL · RAF recovery (50% missing) | Cosine: 0.642 -> 0.783 | Improved |
| add trace norm term (ablation) | HidLDL · Emo recovery (50% missing) | Clark: 1.538 -> 1.249 | Improved |
| add trace norm term (ablation) | HidLDL · cold recovery (50% missing) | Clark: 0.123 -> 0.099 | Improved |
| use HidLDL instead of SA-IIS | HidLDL · RAF recovery (50% missing) | Canberra: 3.0345 (ours) vs 2.9245 (SA-IIS) | Mixed |
| use HidLDL for recovery | HidLDL · 12 datasets recovery (50% missing) | Canberra: wins 69 of 72 comparisons | Improved |
| use HidLDL for downstream prediction | HidLDL · 12 datasets prediction (50% missing) | Canberra: wins 66 of 72 comparisons | Improved |
| increase trace-norm alpha beyond 2^5 (ablation) | HidLDL · Emo, dtt, cold, RAF | Cosine | Hurt |
| increase missing rate | HidLDL · recovery | metrics | Hurt |
Closest papers by meaning
- Approximately Correct Label Distribution Learning (ICML 2025 · similarity 0.91)
- Concentration Distribution Learning from Label Distributions (ICML 2025 · similarity 0.88)
- Divide and Conquer: Learning Label Distribution with Subtasks (ICML 2025 · similarity 0.87)
- Generative Calibration of Inaccurate Annotation for Label Distribution Learning (AAAI 2024 · similarity 0.86)
- GLDL: Graph Label Distribution Learning (AAAI 2024 · similarity 0.85)
- LIMEFLDL: A Local Interpretable Model-Agnostic Explanations Approach for Label Distribution Learning (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.
