Uncertainty Quantification (UQ) is essential for creating trustworthy machine learning models. Recent years have seen a steep rise in UQ methods that can flag suspicious examples, however, it is often unclear what exactly these methods identify. In this work, we propose a framework for categorizing uncertain examples flagged by UQ methods in classification tasks. We introduce the confusion density matrix -- a kernel-based approximation of the misclassification density -- and use this to categorize suspicious examples identified by a given uncertainty method into three classes: out-of-distribution (OOD) examples, boundary (Bnd) examples, and examples in regions of high in-distribution misclassification (IDM). Through extensive experiments, we show that our framework provides a new and distinct perspective for assessing differences between uncertainty quantification methods, thereby forming a valuable assessment benchmark.
@article{arxiv.2207.05161,
title = {What is Flagged in Uncertainty Quantification? Latent Density Models for Uncertainty Categorization},
author = {Hao Sun and Boris van Breugel and Jonathan Crabbe and Nabeel Seedat and Mihaela van der Schaar},
journal= {arXiv preprint arXiv:2207.05161},
year = {2023}
}