Keywords: uncertainty quantification, label-wise uncertainty, second-order distribution, variance
TL;DR: We present a novel approach to uncertainty quantification in classification tasks based on label-wise decomposition of 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.
List Of Authors: Sale, Yusuf and Hofman, Paul and L\''ohr, Timo and Wimmer, Lisa and Nagler, Thomas and H\''ullermeier, Eyke
Latex Source Code: zip
Signed License Agreement: pdf
Code Url: https://github.com/YSale/label-uq
Submission Number: 686
Loading