Uncertainty Propagation in XAI: A Comparison of Analytical and Empirical Estimators

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chiaburu, Teodor, Bießmann, Felix, Haußer, Frank
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909566702190592
author Chiaburu, Teodor
Bießmann, Felix
Haußer, Frank
author_facet Chiaburu, Teodor
Bießmann, Felix
Haußer, Frank
contents Understanding uncertainty in Explainable AI (XAI) is crucial for building trust and ensuring reliable decision-making in Machine Learning models. This paper introduces a unified framework for quantifying and interpreting Uncertainty in XAI by defining a general explanation function $e_θ(x, f)$ that captures the propagation of uncertainty from key sources: perturbations in input data and model parameters. By using both analytical and empirical estimates of explanation variance, we provide a systematic means of assessing the impact uncertainty on explanations. We illustrate the approach using a first-order uncertainty propagation as the analytical estimator. In a comprehensive evaluation across heterogeneous datasets, we compare analytical and empirical estimates of uncertainty propagation and evaluate their robustness. Extending previous work on inconsistencies in explanations, our experiments identify XAI methods that do not reliably capture and propagate uncertainty. Our findings underscore the importance of uncertainty-aware explanations in high-stakes applications and offer new insights into the limitations of current XAI methods. The code for the experiments can be found in our repository at https://github.com/TeodorChiaburu/UXAI
format Preprint
id arxiv_https___arxiv_org_abs_2504_03736
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Uncertainty Propagation in XAI: A Comparison of Analytical and Empirical Estimators
Chiaburu, Teodor
Bießmann, Felix
Haußer, Frank
Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
Understanding uncertainty in Explainable AI (XAI) is crucial for building trust and ensuring reliable decision-making in Machine Learning models. This paper introduces a unified framework for quantifying and interpreting Uncertainty in XAI by defining a general explanation function $e_θ(x, f)$ that captures the propagation of uncertainty from key sources: perturbations in input data and model parameters. By using both analytical and empirical estimates of explanation variance, we provide a systematic means of assessing the impact uncertainty on explanations. We illustrate the approach using a first-order uncertainty propagation as the analytical estimator. In a comprehensive evaluation across heterogeneous datasets, we compare analytical and empirical estimates of uncertainty propagation and evaluate their robustness. Extending previous work on inconsistencies in explanations, our experiments identify XAI methods that do not reliably capture and propagate uncertainty. Our findings underscore the importance of uncertainty-aware explanations in high-stakes applications and offer new insights into the limitations of current XAI methods. The code for the experiments can be found in our repository at https://github.com/TeodorChiaburu/UXAI
title Uncertainty Propagation in XAI: A Comparison of Analytical and Empirical Estimators
topic Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.03736