Research map / Label-efficient and robust learning / Noisy labels
LANE: Label-Aware Noise Elimination for Fine-Grained Text Classification
Tiberiu Sosea, Cornelia Caragea
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 label-aware margin (ALM) with semantic weights instead of plain AUM weighting (ablation) | LANE · RCV1 (20% noise) | micro F1: a boost of 4.2% over LANE−sim | Improved |
| add weighted cross entropy based on ALM (ablation) | LANE · RCV1 (20% noise) | micro F1: 3.2% over LANE−alm | Improved |
| replace hard removal of low-AUM samples with LANE soft weighting (ablation) | AUM · RCV1 (20% noise) | micro F1: 1.8% over AUM | Improved |
| use LANE instead of AUM (ablation) | AUM · SciHTC (original labels) | F1: outperforming AUM by 2.9% and LANE−sim by 1.7% | Improved |
| infer Gaussian threshold dynamically instead of fixed mu=0 (ablation) | LANE · Yelp | accuracy: 64.4 -> 65.2 | Improved |
| infer Gaussian threshold dynamically instead of fixed mu=-1 (ablation) | LANE · Yelp | accuracy: 64.1 -> 65.2 | Improved |
| infer Gaussian threshold dynamically instead of fixed mu=0 (ablation) | LANE · Yahoo | accuracy: 68.1 -> 68.9 | Improved |
| infer Gaussian threshold dynamically instead of fixed mu=-1 (ablation) | LANE · Yahoo | accuracy: 65.1 -> 68.9 | Improved |
| swap BERT backbone for RoBERTa | LANE · GoEmotions | wF1: 66.5 -> 66.8 | Improved |
| add LANE on top of RoBERTa baseline | RoBERTa · Yahoo Answer | accuracy: 75.7 -> 78.9 | Improved |
| use LANE rather than DivideMix | DivideMix · Yahoo Answer | accuracy: 69.17 -> 78.4 | Improved |
| use LANE rather than few-shot Llama-2 | Llama-2 13B · SciHTC (20% noise) | macro F1: 15.1 -> 30.5 | Improved |
Closest papers by meaning
- Deep Noise Label Learning via Effective Rank Reduction (ECCV 2026 · similarity 0.87)
- Fine-Grained Classification With Noisy Labels (CVPR 2023 · similarity 0.87)
- Subclass-Dominant Label Noise: A Counterexample for the Success of Early Stopping (NeurIPS 2023 · similarity 0.87)
- NoiseGPT: Label Noise Detection and Rectification through Probability Curvature (NeurIPS 2024 · similarity 0.86)
- Handling Label Noise via Instance-Level Difficulty Modeling and Dynamic Optimization (NeurIPS 2025 · similarity 0.86)
- Adaptive Integration of Partial Label Learning and Negative Learning for Enhanced Noisy Label Learning (AAAI 2024 · 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.
