AnyLoss: Transforming Classification Metrics into Loss Functions

TL;DR

This paper introduces AnyLoss, a method to convert any confusion matrix-based evaluation metric into a differentiable loss function, enabling direct optimization in neural network training, especially benefiting imbalanced datasets.

Contribution

The paper presents a novel, general-purpose approach to transform non-differentiable metrics into differentiable loss functions using approximation, facilitating direct metric optimization during training.

Findings

Effective in handling imbalanced datasets

Achieves competitive training speed

Demonstrates broad applicability across metrics

Abstract

Many evaluation metrics can be used to assess the performance of models in binary classification tasks. However, most of them are derived from a confusion matrix in a non-differentiable form, making it very difficult to generate a differentiable loss function that could directly optimize them. The lack of solutions to bridge this challenge not only hinders our ability to solve difficult tasks, such as imbalanced learning, but also requires the deployment of computationally expensive hyperparameter search processes in model selection. In this paper, we propose a general-purpose approach that transforms any confusion matrix-based metric into a loss function, \textit{AnyLoss}, that is available in optimization processes. To this end, we use an approximation function to make a confusion matrix represented in a differentiable form, and this approach enables any confusion matrix-based metric to be directly used as a loss function. The mechanism of the approximation function is provided to ensure its operability and the differentiability of our loss functions is proved by suggesting their derivatives. We conduct extensive experiments under diverse neural networks with many datasets, and we demonstrate their general availability to target any confusion matrix-based metrics. Our method, especially, shows outstanding achievements in dealing with imbalanced datasets, and its competitive learning speed, compared to multiple baseline models, underscores its efficiency.