# Identifying Drivers of Predictive Aleatoric Uncertainty

arXiv: https://arxiv.org/abs/2312.07252 · HTML: https://mlsanity.com/paper/2312.07252/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 53 references that are in the map.
- First posted on arXiv 12 Dec 2023.

## Builds on (most cited first, 30 of 30)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges](https://mlsanity.com/paper/2011.06225/) (2020)
- [Transformer Interpretability Beyond Attention Visualization](https://mlsanity.com/paper/2012.09838/) (2020)
- [On the Robustness of Interpretability Methods](https://mlsanity.com/paper/1806.08049/) (2018)
- [Uncertainty as a Form of Transparency: Measuring, Communicating, and Using Uncertainty](https://mlsanity.com/paper/2011.07586/) (2020)
- [Ground Truth Evaluation of Neural Network Explanations with CLEVR-XAI](https://mlsanity.com/paper/2003.07258/) (2020)
- [On the Pitfalls of Heteroscedastic Uncertainty Estimation with Probabilistic Neural Networks](https://mlsanity.com/paper/2203.09168/) (2022)
- [Getting a CLUE: A Method for Explaining Uncertainty Estimates](https://mlsanity.com/paper/2006.06848/) (2020)
- [A Comprehensive Taxonomy for Explainable Artificial Intelligence: A Systematic Survey of Surveys on Methods and Concepts](https://mlsanity.com/paper/2105.07190/) (2021)
- [Explainable Artificial Intelligence: a Systematic Review](https://mlsanity.com/paper/2006.00093/) (2020)
- [Use HiResCAM instead of Grad-CAM for faithful explanations of convolutional neural networks](https://mlsanity.com/paper/2011.08891/) (2020)
- [Trustworthy clinical AI solutions: a unified review of uncertainty quantification in deep learning models for medical image analysis](https://mlsanity.com/paper/2210.03736/) (2022)
- [MiVOLO: Multi-input Transformer for Age and Gender Estimation](https://mlsanity.com/paper/2307.04616/) (2023)
- [Explaining Predictive Uncertainty with Information Theoretic Shapley Values](https://mlsanity.com/paper/2306.05724/) (2023)
- [FP-Age: Leveraging Face Parsing Attention for Facial Age Estimation in the Wild](https://mlsanity.com/paper/2106.11145/) (2021)
- [Diverse, Global and Amortised Counterfactual Explanations for Uncertainty Estimates](https://mlsanity.com/paper/2112.02646/) (2021)
- [Optimal Training of Mean Variance Estimation Neural Networks](https://mlsanity.com/paper/2302.08875/) (2023)
- [When Does Uncertainty Matter?: Understanding the Impact of Predictive Uncertainty in ML Assisted Decision Making](https://mlsanity.com/paper/2011.06167/) (2020)
- [Quantifying and Explaining Machine Learning Uncertainty in Predictive Process Monitoring: An Operations Research Perspective](https://mlsanity.com/paper/2304.06412/) (2023)
- [Understanding Pathologies of Deep Heteroskedastic Regression](https://mlsanity.com/paper/2306.16717/) (2023)
- [A probabilistic data-driven model for planar pushing](https://mlsanity.com/paper/1704.03033/) (2017)
- [Monitoring Model Deterioration with Explainable Uncertainty Estimation via Non-parametric Bootstrap](https://mlsanity.com/paper/2201.11676/) (2022)
- [Attribution of Predictive Uncertainties in Classification Models](https://mlsanity.com/paper/2107.08756/) (2021)
- [Gradient-based Uncertainty Attribution for Explainable Bayesian Deep Learning](https://mlsanity.com/paper/2304.04824/) (2023)
- [Large-scale Heteroscedastic Regression via Gaussian Process](https://mlsanity.com/paper/1811.01179/) (2018)

## Built on by (most cited first, 4 of 4)

- [Unveil Sources of Uncertainty: Feature Contribution to Conformal Prediction Intervals](https://mlsanity.com/paper/2505.13118/) (2025)
- [Predictive Multiplicity in Survival Models: A Method for Quantifying Model Uncertainty in Predictive Maintenance Applications](https://mlsanity.com/paper/2504.12156/) (2025)
- [No Single Metric Tells the Whole Story: A Multi-Dimensional Evaluation Framework for Uncertainty Attributions](https://mlsanity.com/paper/2603.24524/) (2026)
- [XU-RS: Explaining Credal Width in Random-Set Language Models](https://mlsanity.com/paper/2609.37594/) (2026)

## Abstract (arXiv)

Explainability and uncertainty quantification are key to trustable artificial intelligence. However, the reasoning behind uncertainty estimates is generally left unexplained. Identifying the drivers of uncertainty complements explanations of point predictions in recognizing model limitations and enhancing transparent decision-making. So far, explanations of uncertainties have been rarely studied. The few exceptions rely on Bayesian neural networks or technically intricate approaches, such as auxiliary generative models, thereby hindering their broad adoption. We propose a straightforward approach to explain predictive aleatoric uncertainties. We estimate uncertainty in regression as predictive variance by adapting a neural network with a Gaussian output distribution. Subsequently, we apply out-of-the-box explainers to the model's variance output. This approach can explain uncertainty influences more reliably than complex published approaches, which we demonstrate in a synthetic setting with a known data-generating process. We substantiate our findings with a nuanced, quantitative benchmark including synthetic and real, tabular and image datasets. For this, we adapt metrics from conventional XAI research to uncertainty explanations. Overall, the proposed method explains uncertainty estimates with little modifications to the model architecture and outperforms more intricate methods in most settings.