A natural way of estimating heteroscedastic label noise in regression is to model the observed (potentially noisy) target as a sample from a normal distribution, whose parameters can be learned by minimizing the negative log-likelihood. This formulation has desirable loss attenuation properties, as it reduces the contribution of high-error examples. Intuitively, this behavior can improve robustness against label noise by reducing overfitting. We propose an extension of this simple and probabilistic approach to classification that has the same desirable loss attenuation properties. Furthermore, we discuss and address some practical challenges of this extension. We evaluate the effectiveness of the method by measuring its robustness against label noise in classification. We perform enlightening experiments exploring the inner workings of the method, including sensitivity to hyperparameters, ablation studies, and other insightful analyses.

翻译：一种估计回归中异方差标签噪声的自然方法是将观测到的（可能含噪）目标变量建模为正态分布的样本，其参数可通过最小化负对数似然进行学习。该建模方式具有理想的损失衰减特性，能降低高误差样本的贡献度。直观而言，这种特性可通过减少过拟合提升对标签噪声的鲁棒性。我们提出将此简洁的概率化方法扩展至分类任务，使其同样具备上述损失衰减特性。此外，我们将讨论并解决该扩展方法在实际应用中的若干挑战。通过测量分类任务中标签噪声的鲁棒性来评估该方法有效性，并开展揭示其内在运行机制的启发性实验，包括超参数敏感性分析、消融研究及其他深入探讨。