mlsanityData to 7 Oct 2026

Stabilizing Estimates of Shapley Values with Control Variates

arXiv 2310.07672 ↗First posted 11 Oct 2023stat.ML cs.LGcited by 9

Not on the map. Why?

Abstract (arXiv)

Shapley values are among the most popular tools for explaining predictions of blackbox machine learning models. However, their high computational cost motivates the use of sampling approximations, inducing a considerable degree of uncertainty. To stabilize these model explanations, we propose ControlSHAP, an approach based on the Monte Carlo technique of control variates. Our methodology is applicable to any machine learning model and requires virtually no extra computation or modeling effort. On several high-dimensional datasets, we find it can produce dramatic reductions in the Monte Carlo variability of Shapley estimates.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 20 of its 42 references that are in the map. First posted on arXiv 11 Oct 2023.

Builds on

20 of 42 references.

References · 20

  1. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  2. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  3. 2019The many Shapley values for model explanationcited by 341
  4. 2019Explaining individual predictions when features are dependent: More accurate approximations to Shapley valuescited by 205
  5. 2020Improving KernelSHAP: Practical Shapley Value Estimation via Linear Regressioncited by 153
  6. 2020True to the Model or True to the Data?cited by 123
  7. 2021FastSHAP: Real-Time Shapley Value Estimationcited by 123
  8. 2021Sampling Permutations for Shapley Value Estimationcited by 101
  9. 2018L-Shapley and C-Shapley: Efficient Model Interpretation for Structured Datacited by 100
  10. 2020Principles and Practice of Explainable Machine Learningcited by 99
  11. 2020Neuron Shapley: Discovering the Responsible Neuronscited by 98
  12. 2019Unrestricted Permutation forces Extrapolation: Variable Importance Requires at least One More Model, or There Is No Free Variable Importancecited by 85
8 more
  1. 2014Control functionals for Monte Carlo integrationcited by 59
  2. 2021S-LIME: Stabilized-LIME for Model Explanationcited by 52
  3. 2019Issues with post-hoc counterfactual explanations: a discussioncited by 30
  4. 2015Sparse Projection Oblique Randomer Forestscited by 15
  5. 2020Understanding Global Feature Contributions With Additive Importance Measurescited by 10
  6. 2018Approximation Trees: Statistical Stability in Model Distillationcited by 9
  7. 2023Crime Prediction Using Machine Learning and Deep Learning: A Systematic Review and Future Directionscited by 8
  8. 2021Exact Shapley Values for Local and Model-True Explanations of Decision Tree Ensemblescited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 3; 2026: 4.

9 papers.

  1. 2024Statistical Significance of Feature Importance Rankingscited by 7
  2. 2024Improving the Weighting Strategy in KernelSHAPcited by 5
  3. 2025shapr: Explaining Machine Learning Models with Conditional Shapley Values in R and Pythoncited by 5
  4. 2025On the Fragility of Contribution Score Computation in Federated Learningcited by 1
  5. 2025Antithetic Sampling for Top-k Shapley Identificationcited by 0
  6. 2026Beyond performance-wise Contribution Evaluation in Federated Learningcited by 0
  7. 2026Challenges in Enabling Private Data Valuationcited by 0
  8. 2026Rethinking XAI Evaluation: A Human-Centered Audit of Shapley Benchmarks in High-Stakes Settingscited by 0
  9. 2026Measuring Explainer Stability via Attribution Separabilitycited by 0