arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1712.09482stat.MLcs.LG
收藏

标签噪声下深度神经网络的鲁棒损失函数

Robust Loss Functions under Label Noise for Deep Neural Networks

Microsoft(微软);Indian Institute of Science(印度科学理工学院)

Aritra Ghosh, Himanshu Kumar, P. S. Sastry

摘要:

在分类器学习的许多应用中,训练数据都会受到标签噪声的影响。深度网络是使用大量训练数据学习的,其中噪声标签的问题特别相关。目前提出的用于在标签噪声下学习深度网络的技术集中在修改网络架构和从噪声标签中估计真实标签的算法上。另一种方法是寻找固有噪声容限的损失函数。对于二进制分类,存在对标签噪声鲁棒的损失函数的理论结果。在本文中,我们提供了一些充分条件的损失函数,使风险最小化下的损失函数将固有的宽容标签噪声的多类分类问题。这些结果推广了现有的结果对二进制分类的噪声容忍损失函数。我们研究了深度网络中一些广泛使用的损失函数,并表明基于误差平均绝对值的损失函数对标签噪声具有内在的鲁棒性。因此,即使在标签噪声下,标准的反向传播也足以学习真正的分类器。通过实验,我们说明了鲁棒性的风险最小化与这样的损失函数的学习神经网络。

英文摘要:

In many applications of classifier learning, training data suffers from label noise. Deep networks are learned using huge training data where the problem of noisy labels is particularly relevant. The current techniques proposed for learning deep networks under label noise focus on modifying the network architecture and on algorithms for estimating true labels from noisy labels. An alternate approach would be to look for loss functions that are inherently noise-tolerant. For binary classification there exist theoretical results on loss functions that are robust to label noise. In this paper, we provide some sufficient conditions on a loss function so that risk minimization under that loss function would be inherently tolerant to label noise for multiclass classification problems. These results generalize the existing results on noise-tolerant loss functions for binary classification. We study some of the widely used loss functions in deep networks and show that the loss function based on mean absolute value of error is inherently robust to label noise. Thus standard back propagation is enough to learn the true classifier even under label noise. Through experiments, we illustrate the robustness of risk minimization with such loss functions for learning neural networks.

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。

↑