# Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Rates

arXiv: https://arxiv.org/abs/1910.03231 · HTML: https://mlsanity.com/paper/1910.03231/

## Key facts

- Cited by 142 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Oct 2019.

## Built on by (most cited first, 30 of 142)

- [Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotations](https://mlsanity.com/paper/2110.12088/) (2021)
- [Provably End-to-end Label-Noise Learning without Anchor Points](https://mlsanity.com/paper/2102.02400/) (2021)
- [UNICON: Combating Label Noise Through Uniform Selection and Contrastive Learning](https://mlsanity.com/paper/2203.14542/) (2022)
- [LLM Unlearning via Loss Adjustment with Only Forget Data](https://mlsanity.com/paper/2410.11143/) (2024)
- [Generalized Jensen-Shannon Divergence Loss for Learning with Noisy Labels](https://mlsanity.com/paper/2105.04522/) (2021)
- [To Smooth or Not? When Label Smoothing Meets Noisy Labels](https://mlsanity.com/paper/2106.04149/) (2021)
- [Clusterability as an Alternative to Anchor Points When Learning with Noisy Labels](https://mlsanity.com/paper/2102.05291/) (2021)
- [Learning Noise Transition Matrix from Only Noisy Labels via Total Variation Regularization](https://mlsanity.com/paper/2102.02414/) (2021)
- [Detecting Corrupted Labels Without Training a Model to Predict](https://mlsanity.com/paper/2110.06283/) (2021)
- [Self-Guided Noise-Free Data Generation for Efficient Zero-Shot Learning](https://mlsanity.com/paper/2205.12679/) (2022)
- [Instance-Dependent Label-Noise Learning with Manifold-Regularized Transition Matrix Estimation](https://mlsanity.com/paper/2206.02791/) (2022)
- [ProMix: Combating Label Noise via Maximizing Clean Sample Utility](https://mlsanity.com/paper/2207.10276/) (2022)
- [Asymmetric Loss Functions for Learning with Noisy Labels](https://mlsanity.com/paper/2106.03110/) (2021)
- [Mitigating Memorization of Noisy Labels by Clipping the Model Prediction](https://mlsanity.com/paper/2212.04055/) (2022)
- [Exploring Criteria of Loss Reweighting to Enhance LLM Unlearning](https://mlsanity.com/paper/2505.11953/) (2025)
- [TransFGU: A Top-down Approach to Fine-Grained Unsupervised Semantic Segmentation](https://mlsanity.com/paper/2112.01515/) (2021)
- [Contrastive Learning Improves Model Robustness Under Label Noise](https://mlsanity.com/paper/2104.08984/) (2021)
- [Self-Filtering: A Noise-Aware Sample Selection for Label Noise with Confidence Penalization](https://mlsanity.com/paper/2208.11351/) (2022)
- [Measuring and Reducing LLM Hallucination without Gold-Standard Answers](https://mlsanity.com/paper/2402.10412/) (2024)
- [Estimating Instance-dependent Bayes-label Transition Matrix using a Deep Neural Network](https://mlsanity.com/paper/2105.13001/) (2021)
- [To Aggregate or Not? Learning with Separate Noisy Labels](https://mlsanity.com/paper/2206.07181/) (2022)
- [The Rich Get Richer: Disparate Impact of Semi-Supervised Learning](https://mlsanity.com/paper/2110.06282/) (2021)
- [Beyond Images: Label Noise Transition Matrix Estimation for Tasks with Lower-Quality Features](https://mlsanity.com/paper/2202.01273/) (2022)
- [Mitigating Memorization of Noisy Labels via Regularization between Representations](https://mlsanity.com/paper/2110.09022/) (2021)
- [Understanding Instance-Level Label Noise: Disparate Impacts and Treatments](https://mlsanity.com/paper/2102.05336/) (2021)
- [WBCAtt: A White Blood Cell Dataset Annotated with Detailed Morphological Attributes](https://mlsanity.com/paper/2306.13531/) (2023)
- [Learning with Noisy Labels by Efficient Transition Matrix Estimation to Combat Label Miscorrection](https://mlsanity.com/paper/2111.14932/) (2021)
- [Understanding the Interaction of Adversarial Training with Noisy Labels](https://mlsanity.com/paper/2102.03482/) (2021)
- [A Tale Of Two Long Tails](https://mlsanity.com/paper/2107.13098/) (2021)
- [Identifying Hard Noise in Long-Tailed Sample Distribution](https://mlsanity.com/paper/2207.13378/) (2022)

## Abstract (arXiv)

Learning with noisy labels is a common challenge in supervised learning. Existing approaches often require practitioners to specify noise rates, i.e., a set of parameters controlling the severity of label noises in the problem, and the specifications are either assumed to be given or estimated using additional steps. In this work, we introduce a new family of loss functions that we name as peer loss functions, which enables learning from noisy labels and does not require a priori specification of the noise rates. Peer loss functions work within the standard empirical risk minimization (ERM) framework. We show that, under mild conditions, performing ERM with peer loss functions on the noisy dataset leads to the optimal or a near-optimal classifier as if performing ERM over the clean training data, which we do not have access to. We pair our results with an extensive set of experiments. Peer loss provides a way to simplify model development when facing potentially noisy training labels, and can be promoted as a robust candidate loss function in such situations.