mlsanityData to 14 Oct 2026

Reducing Aleatoric and Epistemic Uncertainty through Multi-modal Data Acquisition

arXiv 2501.18268 ↗First posted 30 Jan 2025cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

To generate accurate and reliable predictions, modern AI systems need to combine data from multiple modalities, such as text, images, audio, spreadsheets, and time series. Multi-modal data introduces new opportunities and challenges for disentangling uncertainty: it is commonly assumed in the machine learning community that epistemic uncertainty can be reduced by collecting more data, while aleatoric uncertainty is irreducible. However, this assumption is challenged in modern AI systems when information is obtained from different modalities. This paper introduces an innovative data acquisition framework where uncertainty disentanglement leads to actionable decisions, allowing sampling in two directions: sample size and data modality. The main hypothesis is that aleatoric uncertainty decreases as the number of modalities increases, while epistemic uncertainty decreases by collecting more observations. We provide proof-of-concept implementations on two multi-modal datasets to showcase our data acquisition framework, which combines ideas from active learning, active feature acquisition and uncertainty quantification.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 41 of its 88 references that are in the map. First posted on arXiv 30 Jan 2025.

Builds on

41 of 88 references.

References · 41

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  3. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,352
  4. 2020Energy-based Out-of-distribution Detectioncited by 1,299
  5. 2017Multimodal Machine Learning: A Survey and Taxonomycited by 1,013
  6. 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 913
  7. 2018Evidential Deep Learning to Quantify Classification Uncertaintycited by 732
  8. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 600
  9. 2018Predictive Uncertainty Estimation via Prior Networkscited by 557
  10. 2020Classification with Valid and Adaptive Coveragecited by 396
  11. 2021Laplace Redux -- Effortless Bayesian Deep Learningcited by 365
  12. 2016Least Ambiguous Set-Valued Classifiers with Bounded Error Levelscited by 272
29 more
  1. 2020Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-Countscited by 164
  2. 2022Active Learning on a Budget: Opposite Strategies Suit High and Low Budgetscited by 133
  3. 2022Quantifying Aleatoric and Epistemic Uncertainty in Machine Learning: Are Conditional Entropy and Mutual Information Appropriate Measures?cited by 125
  4. 2022Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questionscited by 116
  5. 2023Class-Conditional Conformal Prediction with Many Classescited by 109
  6. 2019Reverse KL-Divergence Training of Prior Networks: Improved Uncertainty and Adversarial Robustnesscited by 104
  7. 2019DropConnect Is Effective in Modeling Uncertainty of Bayesian Deep Networkscited by 92
  8. 2024Benchmarking Uncertainty Disentanglement: Specialized Uncertainties for Specialized Taskscited by 78
  9. 2021Prior and Posterior Networks: A Survey on Evidential Deep Learning Methods For Uncertainty Estimationcited by 71
  10. 2022Pitfalls of Epistemic Uncertainty Quantification through Loss Minimisationcited by 66
  11. 2020Active Feature Acquisition with Generative Surrogate Modelscited by 54
  12. 2020Aleatoric and Epistemic Uncertainty with Random Forestscited by 43
  13. 2022The Unreasonable Effectiveness of Deep Evidential Regressioncited by 40
  14. 2021Active Learning for Sequence Tagging with Deep Pre-trained Models and Bayesian Uncertainty Estimatescited by 39
  15. 2023On Second-Order Scoring Rules for Epistemic Uncertainty Quantificationcited by 38
  16. 2024Is Epistemic Uncertainty Faithfully Represented by Evidential Deep Learning Methods?cited by 35
  17. 2023Introducing an Improved Information-Theoretic Measure of Predictive Uncertaintycited by 28
  18. 2024BIOSCAN-5M: A Multimodal Dataset for Insect Biodiversitycited by 24
  19. 2024Label-wise Aleatoric and Epistemic Uncertainty Quantificationcited by 22
  20. 2024An Information Theoretic Perspective on Conformal Predictioncited by 21
  21. 2023Second-Order Uncertainty Quantification: Variance-Based Measurescited by 19
  22. 2021An evidential classifier based on Dempster-Shafer theory and deep learningcited by 18
  23. 2023Integrating Uncertainty Awareness into Conformalized Quantile Regressioncited by 17
  24. 2023Evidential Uncertainty Quantification: A Variance-Based Perspectivecited by 14
  25. 2022Active Acquisition for Multimodal Temporal Data: A Challenging Decision-Making Taskcited by 13
  26. 2024The Epistemic Uncertainty Hole: an issue of Bayesian Neural Networkscited by 11
  27. 2019Multi-modal Active Learning From Human Data: A Deep Reinforcement Learning Approachcited by 8
  28. 2024Quantifying Aleatoric and Epistemic Dynamics Uncertainty via Local Conformal Calibrationcited by 6
  29. 2024Evidential Uncertainty Sets in Deep Classifiers Using Conformal Predictioncited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 2.

5 papers.

  1. 2025Cohort-Based Active Modality Acquisitioncited by 5
  2. 2025UbiQTree: Uncertainty Quantification in XAI with Tree Ensemblescited by 4
  3. 2025Robust Explanations Through Uncertainty Decomposition: A Path to Trustworthier AIcited by 2
  4. 2026Conditional Validity for Adaptive Modality Acquisition: When the Policy Chooses Its Own Calibration Groupcited by 0
  5. 2026Explanations-Driven Active Feature Acquisition for Algorithmic Recoursecited by 0