Do We Really Need Gold Samples for Sample Weighting Under Label Noise?

TL;DR

This paper demonstrates that training a meta-weighting network for label noise can be effectively achieved without clean samples by using a noise-robust loss function, simplifying practical implementation.

Contribution

It analytically proves that clean samples are unnecessary for training MW-Net when using a robust loss, and empirically shows competitive performance without clean data.

Findings

Outperforms existing methods without clean samples

Matches performance of methods using gold samples

Effective across various noise types and rates

Abstract

Learning with labels noise has gained significant traction recently due to the sensitivity of deep neural networks under label noise under common loss functions. Losses that are theoretically robust to label noise, however, often makes training difficult. Consequently, several recently proposed methods, such as Meta-Weight-Net (MW-Net), use a small number of unbiased, clean samples to learn a weighting function that downweights samples that are likely to have corrupted labels under the meta-learning framework. However, obtaining such a set of clean samples is not always feasible in practice. In this paper, we analytically show that one can easily train MW-Net without access to clean samples simply by using a loss function that is robust to label noise, such as mean absolute error, as the meta objective to train the weighting network. We experimentally show that our method beats all existing methods that do not use clean samples and performs on-par with methods that use gold samples on benchmark datasets across various noise types and noise rates.