论文标题
使用结构化熵进行分类的损失功能
Loss Functions for Classification using Structured Entropy
论文作者
论文摘要
横向渗透损失是用于训练深度学习和梯度提升的标准度量。众所周知，此损耗函数无法说明目标不同值之间的相似性。我们提出了一个称为{\ em结构化熵}的熵的概括，该熵使用随机分区以保留标准熵的许多理论特性的方式使用随机分区结合目标变量的结构。我们表明，在目标变量具有先验已知结构的几个分类问题上，结构化的跨透明损失会产生更好的结果。该方法简单，灵活，易于计算，并且不依赖于层次定义的结构概念。
Cross-entropy loss is the standard metric used to train classification models in deep learning and gradient boosting. It is well-known that this loss function fails to account for similarities between the different values of the target. We propose a generalization of entropy called {\em structured entropy} which uses a random partition to incorporate the structure of the target variable in a manner which retains many theoretical properties of standard entropy. We show that a structured cross-entropy loss yields better results on several classification problems where the target variable has an a priori known structure. The approach is simple, flexible, easily computable, and does not rely on a hierarchically defined notion of structure.
