On Learning Contrastive Representations for Learning with Noisy Labels

TL;DR

This paper introduces a contrastive regularization approach to learn robust data representations that are resistant to noisy labels, improving deep neural network training under label noise conditions.

Contribution

It proposes a novel contrastive regularization function that enhances representation robustness against label noise, supported by theoretical analysis and empirical validation.

Findings

Learned representations retain true label information

Representations are robust to label noise

Method outperforms existing approaches on benchmarks

Abstract

Deep neural networks are able to memorize noisy labels easily with a softmax cross-entropy (CE) loss. Previous studies attempted to address this issue focus on incorporating a noise-robust loss function to the CE loss. However, the memorization issue is alleviated but still remains due to the non-robust CE loss. To address this issue, we focus on learning robust contrastive representations of data on which the classifier is hard to memorize the label noise under the CE loss. We propose a novel contrastive regularization function to learn such representations over noisy data where label noise does not dominate the representation learning. By theoretically investigating the representations induced by the proposed regularization function, we reveal that the learned representations keep information related to true labels and discard information related to corrupted labels. Moreover, our theoretical results also indicate that the learned representations are robust to the label noise. The effectiveness of this method is demonstrated with experiments on benchmark datasets.