Feature Noise Boosts DNN Generalization under Label Noise

TL;DR

This paper proposes a simple feature noise technique that improves deep neural network generalization under label noise by theoretically constraining model complexity and empirically enhancing performance across datasets.

Contribution

It introduces a theoretically grounded feature noise method that enhances DNN robustness to label noise, with analysis of optimal noise types and levels for better generalization.

Findings

Feature noise improves DNN generalization under label noise.

Theoretical analysis links feature noise to PAC-Bayes bounds.

Experimental results show significant performance gains.

Abstract

The presence of label noise in the training data has a profound impact on the generalization of deep neural networks (DNNs). In this study, we introduce and theoretically demonstrate a simple feature noise method, which directly adds noise to the features of training data, can enhance the generalization of DNNs under label noise. Specifically, we conduct theoretical analyses to reveal that label noise leads to weakened DNN generalization by loosening the PAC-Bayes generalization bound, and feature noise results in better DNN generalization by imposing an upper bound on the mutual information between the model weights and the features, which constrains the PAC-Bayes generalization bound. Furthermore, to ensure effective generalization of DNNs in the presence of label noise, we conduct application analyses to identify the optimal types and levels of feature noise to add for obtaining desirable label noise generalization. Finally, extensive experimental results on several popular datasets demonstrate the feature noise method can significantly enhance the label noise generalization of the state-of-the-art label noise method.