# A Deeper Look into Aleatoric and Epistemic Uncertainty Disentanglement

arXiv: https://arxiv.org/abs/2204.09308 · HTML: https://mlsanity.com/paper/2204.09308/

## Key facts

- Cited by 87 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 25 references that are in the map.
- First posted on arXiv 20 Apr 2022.

## Builds on (most cited first, 11 of 11)

- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift](https://mlsanity.com/paper/1906.02530/) (2019)
- [Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methods](https://mlsanity.com/paper/1910.09457/) (2019)
- [A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges](https://mlsanity.com/paper/2011.06225/) (2020)
- [Challenges in Representation Learning: A report on three machine learning contests](https://mlsanity.com/paper/1307.0414/) (2013)
- [Computer Vision for Autonomous Vehicles: Problems, Datasets and State of the Art](https://mlsanity.com/paper/1704.05519/) (2017)
- [Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batches](https://mlsanity.com/paper/1803.04386/) (2018)
- [On the Pitfalls of Heteroscedastic Uncertainty Estimation with Probabilistic Neural Networks](https://mlsanity.com/paper/2203.09168/) (2022)
- [DropConnect Is Effective in Modeling Uncertainty of Bayesian Deep Networks](https://mlsanity.com/paper/1906.04569/) (2019)

## Built on by (most cited first, 30 of 87)

- [Benchmarking Uncertainty Disentanglement: Specialized Uncertainties for Specialized Tasks](https://mlsanity.com/paper/2402.19460/) (2024)
- [Estimating Epistemic and Aleatoric Uncertainty with a Single Model](https://mlsanity.com/paper/2402.03478/) (2024)
- [Is one annotation enough? A data-centric image classification benchmark for noisy and ambiguous label estimation](https://mlsanity.com/paper/2207.06214/) (2022)
- [Rethinking Aleatoric and Epistemic Uncertainty](https://mlsanity.com/paper/2412.20892/) (2024)
- [Position: Uncertainty Quantification Needs Reassessment for Large-language Model Agents](https://mlsanity.com/paper/2505.22655/) (2025)
- [MAQA: Evaluating Uncertainty Quantification in LLMs Regarding Data Uncertainty](https://mlsanity.com/paper/2408.06816/) (2024)
- [Reality Check: A New Evaluation Ecosystem Is Necessary to Understand AI's Real World Effects](https://mlsanity.com/paper/2505.18893/) (2025)
- [Hyperbolic Active Learning for Semantic Segmentation under Domain Shift](https://mlsanity.com/paper/2306.11180/) (2023)
- [On Information-Theoretic Measures of Predictive Uncertainty](https://mlsanity.com/paper/2410.10786/) (2024)
- [Efficient Process Reward Model Training via Active Learning](https://mlsanity.com/paper/2504.10559/) (2025)
- [Materials Property Prediction with Uncertainty Quantification: A Benchmark Study](https://mlsanity.com/paper/2211.02235/) (2022)
- [Zero-shot Imputation with Foundation Inference Models for Dynamical Systems](https://mlsanity.com/paper/2402.07594/) (2024)
- [Active operator learning with predictive uncertainty quantification for partial differential equations](https://mlsanity.com/paper/2503.03178/) (2025)
- [One step closer to unbiased aleatoric uncertainty estimation](https://mlsanity.com/paper/2312.10469/) (2023)
- [Pretrained Visual Uncertainties](https://mlsanity.com/paper/2402.16569/) (2024)
- [An Axiomatic Assessment of Entropy- and Variance-based Uncertainty Quantification in Regression](https://mlsanity.com/paper/2504.18433/) (2025)
- [Position: Epistemic uncertainty estimation methods are fundamentally incomplete](https://mlsanity.com/paper/2505.23506/) (2025)
- [Multi-Head Multi-Loss Model Calibration](https://mlsanity.com/paper/2303.01099/) (2023)
- [Body Knowledge and Uncertainty Modeling for Monocular 3D Human Body Reconstruction](https://mlsanity.com/paper/2308.00799/) (2023)
- [Estimating Ego-Body Pose from Doubly Sparse Egocentric Video Data](https://mlsanity.com/paper/2411.03561/) (2024)
- [Uncertainty Quantification in Machine Learning for Biosignal Applications -- A Review](https://mlsanity.com/paper/2312.09454/) (2023)
- [A Review of Bayesian Uncertainty Quantification in Deep Probabilistic Image Segmentation](https://mlsanity.com/paper/2411.16370/) (2024)
- [CLEAR: Calibrated Learning for Epistemic and Aleatoric Risk](https://mlsanity.com/paper/2507.08150/) (2025)
- [Uncertainty Quantification for Gradient-based Explanations in Neural Networks](https://mlsanity.com/paper/2403.17224/) (2024)
- [LUMA: A Benchmark Dataset for Learning from Uncertain and Multimodal Data](https://mlsanity.com/paper/2406.09864/) (2024)
- [Uncertainty Unveiled: Can Exposure to More In-context Examples Mitigate Uncertainty for Large Language Models?](https://mlsanity.com/paper/2505.21003/) (2025)
- [Uncertainty Quantification for Regression using Proper Scoring Rules](https://mlsanity.com/paper/2509.26610/) (2025)
- [Deep Gaussian Mixture Ensembles](https://mlsanity.com/paper/2306.07235/) (2023)
- [On the Impact of Uncertainty and Calibration on Likelihood-Ratio Membership Inference Attacks](https://mlsanity.com/paper/2402.10686/) (2024)
- [Uncertainty Quantification on Graph Learning: A Survey](https://mlsanity.com/paper/2404.14642/) (2024)

## Abstract (arXiv)

Neural networks are ubiquitous in many tasks, but trusting their predictions is an open issue. Uncertainty quantification is required for many applications, and disentangled aleatoric and epistemic uncertainties are best. In this paper, we generalize methods to produce disentangled uncertainties to work with different uncertainty quantification methods, and evaluate their capability to produce disentangled uncertainties. Our results show that: there is an interaction between learning aleatoric and epistemic uncertainty, which is unexpected and violates assumptions on aleatoric uncertainty, some methods like Flipout produce zero epistemic uncertainty, aleatoric uncertainty is unreliable in the out-of-distribution setting, and Ensembles provide overall the best disentangling quality. We also explore the error produced by the number of samples hyper-parameter in the sampling softmax function, recommending N > 100 samples. We expect that our formulation and results help practitioners and researchers choose uncertainty methods and expand the use of disentangled uncertainties, as well as motivate additional research into this topic.