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 loss has desirable loss attenuation properties, as it can reduce 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. 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 more.

翻译：在回归任务中，估计异方差标签噪声的一种自然方式是将观测到的（可能含噪）目标变量建模为正态分布的样本，通过最小化负对数似然学习其参数。该损失函数具有理想的损失衰减特性，可降低高误差样本的贡献。直观上，这种特性通过减少过拟合来提升对标签噪声的鲁棒性。我们提出将该简单概率方法扩展至分类任务，使其同样具备上述损失衰减特性。通过测量分类任务中对标签噪声的鲁棒性来评估方法有效性，并开展揭示方法内在机理的启发性实验，包括超参数敏感性分析、消融研究等。