mlsanityData to 14 Oct 2026

Explaining Predictive Uncertainty with Information Theoretic Shapley Values

arXiv 2306.05724 ↗First posted 9 Jun 2023stat.ML cs.LGcited by 36

Not on the map. Why?

Abstract (arXiv)

Researchers in explainable artificial intelligence have developed numerous methods for helping users understand the predictions of complex supervised learning models. By contrast, explaining the textituncertainty of model outputs has received relatively little attention. We adapt the popular Shapley value framework to explain various types of predictive uncertainty, quantifying each feature's contribution to the conditional entropy of individual model outputs. We consider games with modified characteristic functions and find deep connections between the resulting Shapley values and fundamental quantities from information theory and conditional independence testing. We outline inference procedures for finite sample error rate control with provable guarantees, and implement efficient algorithms that perform well in a range of experiments on real and simulated data. Our method has applications to covariate shift detection, active learning, feature selection, and active feature-value acquisition.

Key facts. Cited by 36 papers in the map (data through 14 Oct 2026). Builds on 58 of its 96 references that are in the map. First posted on arXiv 9 Jun 2023.

Builds on

58 of 96 references.

References · 58

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  4. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,166
  5. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  6. 2017On Calibration of Modern Neural Networkscited by 4,960
  7. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  8. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  9. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  10. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,323
  11. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,287
  12. 2018Sanity Checks for Saliency Mapscited by 1,156
38 more
  1. 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,089
  2. 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 913
  3. 2016The Mythos of Model Interpretabilitycited by 721
  4. 2016Distribution-Free Predictive Inference For Regressioncited by 668
  5. 2019Explaining Machine Learning Classifiers through Diverse Counterfactual Explanationscited by 614
  6. 2016Deep Exploration via Bootstrapped DQNcited by 527
  7. 2019BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learningcited by 432
  8. 2019The many Shapley values for model explanationcited by 344
  9. 2018Learning to Explain: An Information-Theoretic Perspective on Model Interpretationcited by 248
  10. 2020Explaining by Removing: A Unified Framework for Model Explanationcited by 218
  11. 2019Explaining individual predictions when features are dependent: More accurate approximations to Shapley valuescited by 208
  12. 2019Model-Agnostic Counterfactual Explanations for Consequential Decisionscited by 204
  13. 2018Understanding Measures of Uncertainty for Adversarial Example Detectioncited by 177
  14. 2022Uncertainty Quantification in Scientific Machine Learning: Methods, Metrics, and Comparisonscited by 170
  15. 2019Feature relevance quantification in explainable AI: A causal problemcited by 167
  16. 2020Improving KernelSHAP: Practical Shapley Value Estimation via Linear Regressioncited by 154
  17. 2021Testing for Outliers with Conformal p-valuescited by 134
  18. 2020True to the Model or True to the Data?cited by 126
  19. 2020Reliable Post hoc Explanations: Modeling Uncertainty in Explainabilitycited by 125
  20. 2022Quantifying Aleatoric and Epistemic Uncertainty in Machine Learning: Are Conditional Entropy and Mutual Information Appropriate Measures?cited by 125
  21. 2022Algorithms to estimate Shapley value feature attributionscited by 115
  22. 2021Machine Learning with a Reject Option: A surveycited by 109
  23. 2020Causal Shapley Values: Exploiting Causal Knowledge to Explain Individual Predictions of Complex Modelscited by 107
  24. 2018L-Shapley and C-Shapley: Efficient Model Interpretation for Structured Datacited by 100
  25. 2020Getting a CLUE: A Method for Explaining Uncertainty Estimatescited by 92
  26. 2020On the Tractability of SHAP Explanationscited by 92
  27. 2019Unrestricted Permutation forces Extrapolation: Variable Importance Requires at least One More Model, or There Is No Free Variable Importancecited by 87
  28. 2022Impossibility Theorems for Feature Attributioncited by 78
  29. 2020Efficient nonparametric statistical inference on population feature importance using Shapley valuescited by 61
  30. 2022From Shapley Values to Generalized Additive Models and backcited by 60
  31. 2021Have We Learned to Explain?: How Interpretability Methods Can Learn to Encode Predictions in their Interpretationscited by 59
  32. 2020BayLIME: Bayesian Local Interpretable Model-Agnostic Explanationscited by 51
  33. 2013Strong Completeness and Faithfulness in Bayesian Networkscited by 45
  34. 2021Local Explanations via Necessity and Sufficiency: Unifying Theory and Practicecited by 45
  35. 2013Context-Specific Independence in Bayesian Networkscited by 43
  36. 2020Aleatoric and Epistemic Uncertainty with Random Forestscited by 43
  37. 2023The Inadequacy of Shapley Values for Explainabilitycited by 31
  38. 2019Addressing Delayed Feedback for Continuous Training with Neural Networks in CTR predictioncited by 25

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 10; 2025: 10; 2026: 14.

36 papers.

Sort:

By area:

  1. 2024shapiq: Shapley Interactions for Machine Learningcited by 43
  2. 2024Uncertainty in Graph Neural Networks: A Surveycited by 23
  3. 2025Anthropomimetic Uncertainty: What Verbalized Uncertainty in Language Models is Missingcited by 14
  4. 2024Explaining Bayesian Optimization by Shapley Values Facilitates Human-AI Collaborationcited by 12
  5. 2024Explaining Predictive Uncertainty by Exposing Second-Order Effectscited by 10
  6. 2024Uncertainty quantification for probabilistic machine learning in earth observation using conformal predictioncited by 9
  7. 2023Model-agnostic variable importance for predictive uncertainty: an entropy-based approachcited by 6
  8. 2025Unveil Sources of Uncertainty: Feature Contribution to Conformal Prediction Intervalscited by 5
  9. 2023Identifying Drivers of Predictive Aleatoric Uncertaintycited by 4
  10. 2024X-Fake: Juggling Utility Evaluation and Explanation of Simulated SAR Imagescited by 4
  11. 2025UbiQTree: Uncertainty Quantification in XAI with Tree Ensemblescited by 4
  12. 2026LLM Performance Predictors: Learning When to Escalate in Hybrid Human-AI Moderation Systemscited by 4
24 more
  1. 2024Investigating the Impact of Model Instability on Explanations and Uncertaintycited by 3
  2. 2024Sufficient and Necessary Explanations (and What Lies in Between)cited by 3
  3. 2025Beyond Shapley Values: Cooperative Games for the Interpretation of Machine Learning Modelscited by 3
  4. 2024A Comprehensive Study of Shapley Value in Data Analyticscited by 2
  5. 2024Segmentation, Classification and Interpretation of Breast Cancer Medical Images using Human-in-the-Loop Machine Learningcited by 1
  6. 2025On Using the Shapley Value for Anomaly Localization: A Statistical Investigationcited by 1
  7. 2025A Systematic Review of Conformal Inference Procedures for Treatment Effect Estimation: Methods and Challengescited by 1
  8. 2026Uncertainty-Aware Multimodal Learning via Conformal Shapley Intervalscited by 1
  9. 2025Conceptualizing Uncertainty: A Concept-based Approach to Explaining Uncertaintycited by 0
  10. 2025Understanding Action Effects through Instrumental Empowerment in Multi-Agent Reinforcement Learningcited by 0
  11. 2025φ-Table: A Statistical Explanation for Global SHAPcited by 0
  12. 2025UbiQVision: Quantifying Uncertainty in XAI for Image Recognitioncited by 0
  13. 2026How important are the genes to explain the outcome - the asymmetric Shapley value as an honest importance metric for high-dimensional featurescited by 0
  14. 2026EviATTA: Evidential Active Test-Time Adaptation for Medical Segment Anything Modelscited by 0
  15. 2026No Single Metric Tells the Whole Story: A Multi-Dimensional Evaluation Framework for Uncertainty Attributionscited by 0
  16. 2026Quantifying and Understanding Uncertainty in Large Reasoning Modelscited by 0
  17. 2026RoSHAP: A Distributional Framework and Robust Metric for Stable Feature Attributioncited by 0
  18. 2026Verified SHAP: Provable Bounds for Exact Shapley Values of Neural Networkscited by 0
  19. 2026Localizing Input Uncertainty Quantification for Large Language Models via Shapley Valuescited by 0
  20. 2026Statistical Analysis of using the Shapley Value for Sensor Anomaly Localization with Accurate Classifierscited by 0
  21. 2026Explainable Uncertainty Estimation for Reliable Medical AIcited by 0
  22. 2026LandscapeSHAP: Which Persistent Homology Class Gets the Credit?cited by 0
  23. 2026A Hierarchy of Entropy-Shapley Games for Multivariate Predictive Uncertaintycited by 0
  24. 2026XU-RS: Explaining Credal Width in Random-Set Language Modelscited by 0