Label noise presents a real challenge for supervised learning algorithms. Consequently, mitigating label noise has attracted immense research in recent years. Noise robust losses is one of the more promising approaches for dealing with label noise, as these methods only require changing the loss function and do not require changing the design of the classifier itself, which can be expensive in terms of development time. In this work we focus on losses that use output regularization (such as label smoothing and entropy). Although these losses perform well in practice, their ability to mitigate label noise lack mathematical rigor. In this work we aim at closing this gap by showing that losses, which incorporate an output regularization term, become symmetric as the regularization coefficient goes to infinity. We argue that the regularization coefficient can be seen as a hyper-parameter controlling the symmetricity, and thus, the noise robustness of the loss function.
翻译:因此,减少标签噪音近年来吸引了大量研究。 噪音强力损失是处理标签噪音的更有希望的方法之一,因为这些方法只需要改变损失功能,而不需要改变分类器本身的设计,因为从开发时间来看,分类器本身的设计可能很昂贵。在这项工作中,我们侧重于使用产出规范化(例如标签平滑和加密)的损失。虽然这些损失在实践中表现良好,但它们减少标签噪音的能力缺乏数学钻孔机。 在这项工作中,我们的目标是通过显示包含产出规范化术语的损失随着正常化系数的无限化而变得对称。 我们争论说,正常化系数可以被视为控制对称性的超参数,因此,可以将噪音稳健性的损失功能视为一种控制对称性的超参数。