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：一种估算回归中异方差标签噪声的自然方法是将观测到的（可能有噪声的）目标模型化为正态分布的样本，其参数可以通过最小化负对数似然来学习。该损失具有令人满意的损失衰减特性，因为它可以降低高误差示例的贡献。直观地讲，这种行为可以通过减少过拟合来提高对标签噪声的鲁棒性。我们提出了这种简单而概率的分类方法的扩展，该方法具有相同的令人满意的损失衰减特性。我们通过衡量其抗标签噪声的鲁棒性来评估该方法的有效性。我们进行了启发式实验，探索了该方法的内部机制，包括对超参数的敏感性，消融研究等。