Label-wise Aleatoric and Epistemic Uncertainty Quantification
This work addresses the problem of accurate uncertainty quantification for classification tasks, particularly in critical domains like medicine, though it appears incremental as it builds on existing uncertainty measures.
The paper tackles uncertainty quantification in classification by proposing a label-wise decomposition approach that quantifies uncertainty at the individual class level, improving cost-sensitive decision-making and understanding of uncertainty sources, with empirical validation on benchmark datasets including medical applications.
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.