# Learning Not to Learn in the Presence of Noisy Labels

arXiv: https://arxiv.org/abs/2002.06541 · HTML: https://mlsanity.com/paper/2002.06541/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Feb 2020.

## Built on by (most cited first, 9 of 9)

- [Differentiable Learning Under Triage](https://mlsanity.com/paper/2103.08902/) (2021)
- [Reinforcement Learning Under Algorithmic Triage](https://mlsanity.com/paper/2109.11328/) (2021)
- [Zero-Shot End-to-End Spoken Language Understanding via Cross-Modal Selective Self-Training](https://mlsanity.com/paper/2305.12793/) (2023)
- [Learning to Combat Noisy Labels via Classification Margins](https://mlsanity.com/paper/2102.00751/) (2021)
- [Model-Agnostic Meta-Learning for EEG Motor Imagery Decoding in Brain-Computer-Interfacing](https://mlsanity.com/paper/2103.08664/) (2021)
- [Learning with Noisy Labels by Adaptive Gradient-Based Outlier Removal](https://mlsanity.com/paper/2306.04502/) (2023)
- [Leveraging Unlabeled Data to Track Memorization](https://mlsanity.com/paper/2212.04461/) (2022)
- [Dropout can Simulate Exponential Number of Models for Sample Selection Techniques](https://mlsanity.com/paper/2202.13203/) (2022)
- [Smoothly Giving up: Robustness for Simple Models](https://mlsanity.com/paper/2302.09114/) (2023)

## Abstract (arXiv)

Learning in the presence of label noise is a challenging yet important task: it is crucial to design models that are robust in the presence of mislabeled datasets. In this paper, we discover that a new class of loss functions called the gambler's loss provides strong robustness to label noise across various levels of corruption. We show that training with this loss function encourages the model to "abstain" from learning on the data points with noisy labels, resulting in a simple and effective method to improve robustness and generalization. In addition, we propose two practical extensions of the method: 1) an analytical early stopping criterion to approximately stop training before the memorization of noisy labels, as well as 2) a heuristic for setting hyperparameters which do not require knowledge of the noise corruption rate. We demonstrate the effectiveness of our method by achieving strong results across three image and text classification tasks as compared to existing baselines.