Research map / Label-efficient and robust learning / Noisy labels
Label Distributionally Robust Losses for Multi-class Classification: Consistency, Robustness and Adaptivity
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 |
|---|---|---|---|
| adaptive per-instance lambda (ALDR-KL) instead of fixed LDR-KL | LDR-KL loss · Webvision mini ILSVRC12 val | top-1 accuracy: 69.92 vs 69.00 | Helped |
| use LDR-KL (fixed lambda, KL regularizer) instead of CE | CE loss · Leaderboard 7 datasets | overall average rank: 2.743 vs 4.473 | Helped |
| adaptive lambda (ALDR-KL) over fixed-lambda LDR-KL | LDR-KL · Leaderboard 7 datasets | overall average rank: 2.331 vs 2.743 | Helped |
| symmetric MAE loss used alone (no consistency) | MAE loss · Leaderboard 7 datasets | overall average rank: 14.49 (worst) | Hurt |
| sets lambda=infinity symmetric LDR-KL is All-k consistent with bounded logits | LDR-KL · theory | consistency | No clear effect |
Closest papers by meaning
- Robust Loss Functions under Label Noise for Deep Neural Networks (AAAI 2017 · similarity 0.88)
- Loss factorization, weakly supervised learning and label noise robustness (ICML 2016 · similarity 0.88)
- Robust Classification via Regression for Learning with Noisy Labels (ICLR 2024 · similarity 0.88)
- Multi-Label Learning with Stronger Consistency Guarantees (NeurIPS 2024 · similarity 0.88)
- Robust Loss Functions for Training Decision Trees with Noisy Labels (AAAI 2024 · similarity 0.87)
- Trading off Consistency and Dimensionality of Convex Surrogates for Multiclass Classification (NeurIPS 2024 · 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.