我们需要惩罚标签噪声学习的损失方差吗？
Do We Need to Penalize Variance of Losses for Learning with Label Noise?
摘要：
最小化平均损失的算法已经被广泛设计用于处理噪声标签。直觉上，当训练样本有限时，惩罚损失的方差将提高算法的稳定性和推广性。有趣的是，我们发现对于带噪声标签的学习问题，方差应该增加。具体而言，增加方差将提高记忆效果，减少错误标签的危害。利用标签噪声转移矩阵，可以很容易地设计正则化器，以减少损失的方差，并插入到许多现有的算法。经验上，通过增加损失的方差，所提出的方法显着提高了合成和真实世界数据集上基线的泛化能力。
英文摘要：
Algorithms which minimize the averaged loss have been widely designed for dealing with noisy labels. Intuitively, when there is a finite training sample, penalizing the variance of losses will improve the stability and generalization of the algorithms. Interestingly, we found that the variance should be increased for the problem of learning with noisy labels. Specifically, increasing the variance will boost the memorization effects and reduce the harmfulness of incorrect labels. By exploiting the label noise transition matrix, regularizers can be easily designed to reduce the variance of losses and be plugged in many existing algorithms. Empirically, the proposed method by increasing the variance of losses significantly improves the generalization ability of baselines on both synthetic and real-world datasets.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
