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.

翻译：训练数据中的标签噪声对深度神经网络（DNN）的泛化能力产生深远影响。在本研究中，我们引入并理论证明了简单的特征噪声方法——通过直接向训练数据的特征添加噪声——能够增强带标签噪声下DNN的泛化性能。具体而言，理论分析表明：标签噪声通过松弛PAC-Bayes泛化界削弱DNN泛化能力，而特征噪声则通过对模型权重与特征之间的互信息施加上界来约束PAC-Bayes泛化界，从而提升DNN泛化能力。此外，为确保DNN在标签噪声存在时实现有效泛化，我们进行了应用分析以确定最优的特征噪声类型与强度，从而获得理想的标签噪声泛化效果。最后，在多个主流数据集上的大量实验结果表明，特征噪声方法能够显著增强当前最优标签噪声方法的泛化性能。