mlsanityData to 7 Oct 2026

A Deeper Look into Aleatoric and Epistemic Uncertainty Disentanglement

arXiv 2204.09308 ↗First posted 20 Apr 2022cs.LG cs.CVcited by 87

Not on the map. Why?

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.

Key facts. Cited by 87 papers in the map (data through 7 Oct 2026). Builds on 11 of its 25 references that are in the map. First posted on arXiv 20 Apr 2022.

Builds on

11 of 25 references.

References · 11

  1. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  2. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  3. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  4. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,274
  5. 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 903
  6. 2020A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challengescited by 813
  7. 2013Challenges in Representation Learning: A report on three machine learning contestscited by 301
  8. 2017Computer Vision for Autonomous Vehicles: Problems, Datasets and State of the Artcited by 182
  9. 2018Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batchescited by 133
  10. 2022On the Pitfalls of Heteroscedastic Uncertainty Estimation with Probabilistic Neural Networkscited by 119
  11. 2019DropConnect Is Effective in Modeling Uncertainty of Bayesian Deep Networkscited by 92

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 5; 2023: 9; 2024: 27; 2025: 28; 2026: 18.

87 papers.

Sort:

By area:

  1. 2024Benchmarking Uncertainty Disentanglement: Specialized Uncertainties for Specialized Taskscited by 78
  2. 2024Estimating Epistemic and Aleatoric Uncertainty with a Single Modelcited by 52
  3. 2022Is one annotation enough? A data-centric image classification benchmark for noisy and ambiguous label estimationcited by 43
  4. 2024Rethinking Aleatoric and Epistemic Uncertaintycited by 40
  5. 2025Position: Uncertainty Quantification Needs Reassessment for Large-language Model Agentscited by 27
  6. 2024MAQA: Evaluating Uncertainty Quantification in LLMs Regarding Data Uncertaintycited by 25
  7. 2023Hyperbolic Active Learning for Semantic Segmentation under Domain Shiftcited by 18
  8. 2025Reality Check: A New Evaluation Ecosystem Is Necessary to Understand AI's Real World Effectscited by 18
  9. 2024On Information-Theoretic Measures of Predictive Uncertaintycited by 16
  10. 2022Materials Property Prediction with Uncertainty Quantification: A Benchmark Studycited by 14
  11. 2025Efficient Process Reward Model Training via Active Learningcited by 14
  12. 2024Zero-shot Imputation with Foundation Inference Models for Dynamical Systemscited by 13
38 more
  1. 2025Active operator learning with predictive uncertainty quantification for partial differential equationscited by 12
  2. 2023One step closer to unbiased aleatoric uncertainty estimationcited by 10
  3. 2024Pretrained Visual Uncertaintiescited by 10
  4. 2025An Axiomatic Assessment of Entropy- and Variance-based Uncertainty Quantification in Regressioncited by 9
  5. 2023Multi-Head Multi-Loss Model Calibrationcited by 8
  6. 2023Body Knowledge and Uncertainty Modeling for Monocular 3D Human Body Reconstructioncited by 8
  7. 2024Estimating Ego-Body Pose from Doubly Sparse Egocentric Video Datacited by 8
  8. 2025Position: Epistemic uncertainty estimation methods are fundamentally incompletecited by 8
  9. 2023Uncertainty Quantification in Machine Learning for Biosignal Applications -- A Reviewcited by 7
  10. 2024A Review of Bayesian Uncertainty Quantification in Deep Probabilistic Image Segmentationcited by 6
  11. 2025CLEAR: Calibrated Learning for Epistemic and Aleatoric Riskcited by 6
  12. 2024Uncertainty Quantification for Gradient-based Explanations in Neural Networkscited by 5
  13. 2024LUMA: A Benchmark Dataset for Learning from Uncertain and Multimodal Datacited by 5
  14. 2025Uncertainty Unveiled: Can Exposure to More In-context Examples Mitigate Uncertainty for Large Language Models?cited by 5
  15. 2025Uncertainty Quantification for Regression using Proper Scoring Rulescited by 5
  16. 2023Deep Gaussian Mixture Ensemblescited by 4
  17. 2024On the Impact of Uncertainty and Calibration on Likelihood-Ratio Membership Inference Attackscited by 4
  18. 2024Measuring Orthogonality as the Blind-Spot of Uncertainty Disentanglementcited by 4
  19. 2023Pedestrian Trajectory Forecasting Using Deep Ensembles Under Sensing Uncertaintycited by 3
  20. 2024Uncertainty Quantification for cross-subject Motor Imagery classificationcited by 3
  21. 2024Uncertainty Quantification on Graph Learning: A Surveycited by 3
  22. 2024Unified Uncertainties: Combining Input, Data and Model Uncertainty into a Single Formulationcited by 3
  23. 2024Adaptive Sampling to Reduce Epistemic Uncertainty Using Prediction Interval-Generation Neural Networkscited by 3
  24. 2025Uncertainty quantification with approximate variational learning for wearable photoplethysmography prediction taskscited by 3
  25. 2025Automated Fetal Biometry Assessment with Deep Ensembles using Sparse-Sampling of 2D Intrapartum Ultrasound Imagescited by 3
  26. 2025HybridFlow: Quantification of Aleatoric and Epistemic Uncertainty with a Single Hybrid Modelcited by 3
  27. 2026TRIAGE: Type-Routed Interventions via Aleatoric-Epistemic Gated Estimation in Robotic Manipulation and Adaptive Perception -- Don't Treat All Uncertainty the Samecited by 3
  28. 2026Random-Set Graph Neural Networkscited by 3
  29. 2022Uncertainty Disentanglement with Non-stationary Heteroscedastic Gaussian Processes for Active Learningcited by 2
  30. 2022A view on model misspecification in uncertainty quantificationcited by 2
  31. 2022Selective classification using a robust meta-learning approachcited by 2
  32. 2024Deep Evidential Learning for Radiotherapy Dose Predictioncited by 2
  33. 2024The Dilemma of Uncertainty Estimation for General Purpose AI in the EU AI Actcited by 2
  34. 2025Reliable uncertainty quantification for 2D/3D anatomical landmark localization using multi-output conformal predictioncited by 2
  35. 2025Streamlining the Development of Active Learning Methods in Real-World Object Detectioncited by 2
  36. 2025Uncertainty Quantification for Regression: A Unified Framework based on kernel scorescited by 2
  37. 2025Credal Graph Neural Networkscited by 2
  38. 2026Probabilistic Precipitation Nowcasting with Rectified Flow Transformerscited by 2

50 most cited of 87 All 87 (JSON)