# Constrained Instance and Class Reweighting for Robust Learning under Label Noise

Source: [Constrained Instance and Class Reweighting for Robust Learning under Label Noise](<https://www.sota2.com/research/paper/68fa6b371e209131cea2cf9d>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T23:43:15.362Z

Authors: Abhishek Kumar, Ehsan Amid

Published: 2021-11-09T21:37:53.000Z

## Abstract

Deep neural networks have shown impressive performance in supervised learning, enabled by their ability to fit well to the provided training data. However, their performance is largely dependent on the quality of the training data and often degrades in the presence of noise. We propose a principled approach for tackling label noise with the aim of assigning importance weights to individual instances and class labels. Our method works by formulating a class of constrained optimization problems that yield simple closed form updates for these importance weights. The proposed optimization problems are solved per mini-batch which obviates the need of storing and updating the weights over the full dataset. Our optimization framework also provides a theoretical perspective on existing label smoothing heuristics for addressing label noise (such as label bootstrapping). We evaluate our method on several benchmark datasets and observe considerable performance gains in the presence of label noise.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Image Classification on CIFAR10 (test) (Symmetric/Asymmetric Robustness)](<https://www.sota2.com/research/sota/image-classification-on-cifar10-test-symmetric-asymmetric-robustness.md>): Image Classification; CIFAR10 (test); Top-1 Acc (Sym, 0.2): 90.79.

- [Image Classification on CIFAR-100 (test) (Symmetric/Asymmetric Robustness)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-test-symmetric-asymmetric-robustness.md>): Image Classification; CIFAR100 (test); Top-1 Acc (Symmetric, 0.2): 70.21.

- [Image Classification on Clothing1M (test)](<https://www.sota2.com/research/sota/image-classification-on-clothing1m-test.md>): Image Classification; Clothing1M (test); Accuracy: 69.53.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2111.05428>)

[PDF](<https://arxiv.org/pdf/2111.05428.pdf>)