mlsanityData to 14 Oct 2026

Label-wise Aleatoric and Epistemic Uncertainty Quantification

arXiv 2406.02354 ↗First posted 4 Jun 2024cs.LG stat.MLcited by 22

Not on the map. Why?

Abstract (arXiv)

We present a novel approach to uncertainty quantification in classification tasks based on label-wise decomposition of uncertainty measures. This label-wise perspective allows uncertainty to be quantified at the individual class level, thereby improving cost-sensitive decision-making and helping understand the sources of uncertainty. Furthermore, it allows to define total, aleatoric, and epistemic uncertainty on the basis of non-categorical measures such as variance, going beyond common entropy-based measures. In particular, variance-based measures address some of the limitations associated with established methods that have recently been discussed in the literature. We show that our proposed measures adhere to a number of desirable properties. Through empirical evaluation on a variety of benchmark data sets -- including applications in the medical domain where accurate uncertainty quantification is crucial -- we establish the effectiveness of label-wise uncertainty quantification.

Key facts. Cited by 22 papers in the map (data through 14 Oct 2026). Builds on 20 of its 50 references that are in the map. First posted on arXiv 4 Jun 2024.

Builds on

20 of 50 references.

References · 20

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  4. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,352
  5. 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 913
  6. 2018Deep Learning for Classical Japanese Literaturecited by 422
  7. 2018Understanding Measures of Uncertainty for Adversarial Example Detectioncited by 177
  8. 2022Quantifying Aleatoric and Epistemic Uncertainty in Machine Learning: Are Conditional Entropy and Mutual Information Appropriate Measures?cited by 125
  9. 2019DropConnect Is Effective in Modeling Uncertainty of Bayesian Deep Networkscited by 92
  10. 2021Prior and Posterior Networks: A Survey on Evidential Deep Learning Methods For Uncertainty Estimationcited by 71
  11. 2018Evaluating Uncertainty Quantification in End-to-End Autonomous Driving Controlcited by 55
  12. 2016On the Safety of Machine Learning: Cyber-Physical Systems, Decision Sciences, and Data Productscited by 52
8 more
  1. 2023Is the Volume of a Credal Set a Good Measure for Epistemic Uncertainty?cited by 40
  2. 2021Active Learning for Sequence Tagging with Deep Pre-trained Models and Bayesian Uncertainty Estimatescited by 39
  3. 2023Second-Order Uncertainty Quantification: A Distance-Based Approachcited by 35
  4. 2022Bayesian Optimization with Conformal Prediction Setscited by 28
  5. 2023Sources of Uncertainty in Supervised Machine Learning -- A Statisticians' Viewcited by 28
  6. 2016Engineering Safety in Machine Learningcited by 24
  7. 2023Evidential Uncertainty Quantification: A Variance-Based Perspectivecited by 14
  8. 2023Robust Bayesian Target Value Optimizationcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 10; 2026: 9.

22 papers.

Sort:

By area:

  1. 2024Rethinking Aleatoric and Epistemic Uncertaintycited by 42
  2. 2024On Information-Theoretic Measures of Predictive Uncertaintycited by 16
  3. 2025Uncertainty Estimation by Flexible Evidential Deep Learningcited by 10
  4. 2025An Axiomatic Assessment of Entropy- and Variance-based Uncertainty Quantification in Regressioncited by 9
  5. 2025Reducing Aleatoric and Epistemic Uncertainty through Multi-modal Data Acquisitioncited by 5
  6. 2025Robustness quantification: a new method for assessing the reliability of the predictions of a classifiercited by 4
  7. 2025Uncertainty Quantification for Machine Learning: One Size Does Not Fit Allcited by 4
  8. 2025HybridFlow: Quantification of Aleatoric and Epistemic Uncertainty with a Single Hybrid Modelcited by 3
  9. 2026Not Just How Much, But Where: Decomposing Epistemic Uncertainty into Per-Class Contributionscited by 2
  10. 2026Quantification of Credal Uncertainty: A Distance-Based Approachcited by 2
  11. 2026Uncertainty Decomposition via Cyclical SG-MCMC and Soft-label Learning for Subjective NLPcited by 2
  12. 2026On the Epistemic Uncertainty of Overparametrized Neural Networkscited by 2
10 more
  1. 2025Trust Me, I Know the Way: Predictive Uncertainty in the Presence of Shortcut Learningcited by 1
  2. 2025Uncertainty Quantification with Proper Scoring Rules: Adjusting Measures to Prediction Taskscited by 1
  3. 2025Advancing Image Classification with Discrete Diffusion Classification Modelingcited by 1
  4. 2026Set-based v.s. Distribution-based Representations of Epistemic Uncertainty: A Comparative Studycited by 1
  5. 2026An Isotropic Approach to Efficient Uncertainty Quantification with Gradient Normscited by 1
  6. 2026Subjective Risk Decomposition: A New View for Uncertainty Quantificationcited by 1
  7. 2024Fine-Grained Uncertainty Quantification via Collisionscited by 0
  8. 2025Uncertainty-Aware Information Pursuit for Interpretable and Reliable Medical Image Analysiscited by 0
  9. 2026When should we trust the annotation? Selective prediction for molecular structure retrieval from mass spectracited by 0
  10. 2026Enhancing the Reliability of Medical AI through Expert-guided Uncertainty Modelingcited by 0