Label-wise Aleatoric and Epistemic Uncertainty Quantification

TL;DR

This paper introduces a label-wise approach to uncertainty quantification in classification, enabling more precise, class-specific uncertainty measures that improve decision-making and address limitations of existing entropy-based methods.

Contribution

It proposes a novel label-wise decomposition of uncertainty measures, including variance-based metrics, enhancing interpretability and applicability in sensitive domains like medicine.

Findings

Effective in medical diagnosis tasks

Outperforms entropy-based methods in uncertainty estimation

Provides more interpretable class-wise uncertainty measures

Abstract

We present a novel approach to uncertainty quantification in classification tasks based on label-wise decomposition of uncertainty measures. This label-wise perspective allows uncertainty to be quantified at the individual class level, thereby improving cost-sensitive decision-making and helping understand the sources of uncertainty. Furthermore, it allows to define total, aleatoric, and epistemic uncertainty on the basis of non-categorical measures such as variance, going beyond common entropy-based measures. In particular, variance-based measures address some of the limitations associated with established methods that have recently been discussed in the literature. We show that our proposed measures adhere to a number of desirable properties. Through empirical evaluation on a variety of benchmark data sets -- including applications in the medical domain where accurate uncertainty quantification is crucial -- we establish the effectiveness of label-wise uncertainty quantification.