Loss Functions for Classification using Structured Entropy

2022/06/14 by Lucena, Brian
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Information Theory (cs.IT) #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · doi:10.48550/arxiv.2206.07122

Abstract

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.

Related

• Enhancing Cross Entropy with a Linearly Adaptive Loss Function for Optimized Classification Performance
• On the relation between Loss Functions and T-Norms
• Regularizing cross entropy loss via minimum entropy and K-L divergence
• Uses and Abuses of the Cross-Entropy Loss: Case Studies in Modern Deep Learning
• Taming the Cross Entropy Loss