mlsanityData to 7 Oct 2026

FastSHAP: Real-Time Shapley Value Estimation

arXiv 2107.07436 ↗First posted 15 Jul 2021stat.ML cs.CV cs.LGcited by 123

Not on the map. Why?

Abstract (arXiv)

Shapley values are widely used to explain black-box models, but they are costly to calculate because they require many model evaluations. We introduce FastSHAP, a method for estimating Shapley values in a single forward pass using a learned explainer model. FastSHAP amortizes the cost of explaining many inputs via a learning approach inspired by the Shapley value's weighted least squares characterization, and it can be trained using standard stochastic gradient optimization. We compare FastSHAP to existing estimation approaches, revealing that it generates high-quality explanations with orders of magnitude speedup.

Key facts. Cited by 123 papers in the map (data through 7 Oct 2026). Builds on 29 of its 53 references that are in the map. First posted on arXiv 15 Jul 2021.

Builds on

29 of 53 references.

References · 29

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  3. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  4. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,120
  5. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  6. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  7. 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
  8. 2017SmoothGrad: removing noise by adding noisecited by 1,097
  9. 2018RISE: Randomized Input Sampling for Explanation of Black-box Modelscited by 825
  10. 2018A Benchmark for Interpretability Methods in Deep Neural Networkscited by 467
  11. 2018Learning to Explain: An Information-Theoretic Perspective on Model Interpretationcited by 248
  12. 2017Real Time Image Saliency for Black Box Classifierscited by 246
17 more
  1. 2020Explaining by Removing: A Unified Framework for Model Explanationcited by 218
  2. 2019Explaining individual predictions when features are dependent: More accurate approximations to Shapley valuescited by 205
  3. 2020fastai: A Layered API for Deep Learningcited by 183
  4. 2019Feature relevance quantification in explainable AI: A causal problemcited by 164
  5. 2020Improving KernelSHAP: Practical Shapley Value Estimation via Linear Regressioncited by 153
  6. 2019Explaining Deep Neural Networks with a Polynomial Time Algorithm for Shapley Values Approximationcited by 115
  7. 2020Restricting the Flow: Information Bottlenecks for Attributioncited by 110
  8. 2021Sampling Permutations for Shapley Value Estimationcited by 101
  9. 2018L-Shapley and C-Shapley: Efficient Model Interpretation for Structured Datacited by 100
  10. 2019CXPlain: Causal Explanations for Model Interpretation under Uncertaintycited by 98
  11. 2020On the Tractability of SHAP Explanationscited by 92
  12. 2020Shapley explainability on the data manifoldcited by 88
  13. 2020Efficient nonparametric statistical inference on population feature importance using Shapley valuescited by 61
  14. 2021Have We Learned to Explain?: How Interpretability Methods Can Learn to Encode Predictions in their Interpretationscited by 59
  15. 2021Shapley Explanation Networkscited by 41
  16. 2018Amortized Inference Regularizationcited by 30
  17. 2019Estimation of the Shapley value by ergodic samplingcited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 15; 2023: 28; 2024: 40; 2025: 26; 2026: 13.

123 papers.

Sort:

By area:

  1. 2022Algorithms to estimate Shapley value feature attributionscited by 114
  2. 2022From Shapley Values to Generalized Additive Models and backcited by 59
  3. 2022Measuring the Effect of Training Data on Deep Learning Predictions via Randomized Experimentscited by 50
  4. 2022Learning to Estimate Shapley Values with Vision Transformerscited by 44
  5. 2024SwitchTab: Switched Autoencoders Are Effective Tabular Learnerscited by 37
  6. 2022WeightedSHAP: analyzing and improving Shapley based feature attributionscited by 36
  7. 2023Approximating the Shapley Value without Marginal Contributionscited by 34
  8. 2023The Inadequacy of Shapley Values for Explainabilitycited by 30
  9. 2024Beyond TreeSHAP: Efficient Computation of Any-Order Shapley Interactions for Tree Ensemblescited by 30
  10. 2022SurvSHAP(t): Time-dependent explanations of machine learning survival modelscited by 24
  11. 2024Provably Accurate Shapley Value Estimation via Leverage Score Samplingcited by 23
  12. 2024KernelSHAP-IQ: Weighted Least-Square Optimization for Shapley Interactionscited by 22
38 more
  1. 2024Stochastic Amortization: A Unified Approach to Accelerate Feature and Data Attributioncited by 21
  2. 2023CoRTX: Contrastive Framework for Real-time Explanationcited by 20
  3. 2023Explaining the Uncertain: Stochastic Shapley Values for Gaussian Process Modelscited by 19
  4. 2023TextGenSHAP: Scalable Post-hoc Explanations in Text Generation with Long Documentscited by 17
  5. 2023IDGI: A Framework to Eliminate Explanation Noise from Integrated Gradientscited by 16
  6. 2023HarsanyiNet: Computing Accurate Shapley Values in a Single Forward Propagationcited by 16
  7. 2023A Comparative Study of Methods for Estimating Conditional Shapley Values and When to Use Themcited by 15
  8. 2023Efficient XAI Techniques: A Taxonomic Surveycited by 14
  9. 2024Locality Alignment Improves Vision-Language Modelscited by 13
  10. 2024IG2: Integrated Gradient on Iterative Gradient Path for Feature Attributioncited by 12
  11. 2025Exact Computation of Any-Order Shapley Interactions for Graph Neural Networkscited by 12
  12. 2023Don't be fooled: label leakage in explanation methods and the importance of their quantitative evaluationcited by 11
  13. 2025Learning to Attribute with Attentioncited by 11
  14. 2023Stabilizing Estimates of Shapley Values with Control Variatescited by 9
  15. 2024Collaborative Performance Prediction for Large Language Modelscited by 9
  16. 2025Attention, Please! PixelSHAP Reveals What Vision-Language Models Actually Focus Oncited by 9
  17. 2022Incremental Permutation Feature Importance (iPFI): Towards Online Explanations on Data Streamscited by 8
  18. 2024Rethinking Explainable Machine Learning as Applied Statisticscited by 8
  19. 2024SHAP values via sparse Fourier representationcited by 8
  20. 2024Feature Responsiveness Scores: Model-Agnostic Explanations for Recoursecited by 8
  21. 2025SHAP Meets Tensor Networks: Provably Tractable Explanations with Parallelismcited by 8
  22. 2024Enhancing Traffic Incident Management with Large Language Models: A Hybrid Machine Learning Approach for Severity Classificationcited by 7
  23. 2022SHAP-XRT: The Shapley Value Meets Conditional Independence Testingcited by 6
  24. 2022Boundary-Aware Uncertainty for Feature Attribution Explainerscited by 6
  25. 2022Trade-off Between Efficiency and Consistency for Removal-based Explanationscited by 6
  26. 2023Efficient GNN Explanation via Learning Removal-based Attributioncited by 6
  27. 2025DUET: Optimizing Training Data Mixtures via Feedback from Unseen Evaluation Taskscited by 6
  28. 2022Feature Importance for Time Series Data: Improving KernelSHAPcited by 5
  29. 2023Interpretable Graph Neural Networks for Tabular Datacited by 5
  30. 2024Identifying Important Group of Pixels using Interactionscited by 5
  31. 2025Unifying Prediction and Explanation in Time-Series Transformers via Shapley-based Pretrainingcited by 5
  32. 2023Efficient SAGE Estimation via Causal Structure Learningcited by 4
  33. 2023Efficient Shapley Values Estimation by Amortization for Text Classificationcited by 4
  34. 2023Approximating Score-based Explanation Techniques Using Conformal Regressioncited by 4
  35. 2023A Refutation of Shapley Values for Explainabilitycited by 4
  36. 2023SHAPNN: Shapley Value Regularized Tabular Neural Networkcited by 4
  37. 2023The Thousand Faces of Explainable AI Along the Machine Learning Life Cycle: Industrial Reality and Current State of Researchcited by 4
  38. 2024On the Inflation of KNN-Shapley Valuecited by 4

50 most cited of 123 All 123 (JSON)