mlsanityData to 7 Oct 2026

Ensembles of Random SHAPs

arXiv 2103.03302 ↗First posted 4 Mar 2021cs.LG stat.MLcited by 8

Not on the map. Why?

Abstract (arXiv)

Ensemble-based modifications of the well-known SHapley Additive exPlanations (SHAP) method for the local explanation of a black-box model are proposed. The modifications aim to simplify SHAP which is computationally expensive when there is a large number of features. The main idea behind the proposed modifications is to approximate SHAP by an ensemble of SHAPs with a smaller number of features. According to the first modification, called ER-SHAP, several features are randomly selected many times from the feature set, and Shapley values for the features are computed by means of "small" SHAPs. The explanation results are averaged to get the final Shapley values. According to the second modification, called ERW-SHAP, several points are generated around the explained instance for diversity purposes, and results of their explanation are combined with weights depending on distances between points and the explained instance. The third modification, called ER-SHAP-RF, uses the random forest for preliminary explanation of instances and determining a feature probability distribution which is applied to selection of features in the ensemble-based procedure of ER-SHAP. Many numerical experiments illustrating the proposed modifications demonstrate their efficiency and properties for local explanation.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 39 of its 65 references that are in the map. First posted on arXiv 4 Mar 2021.

Builds on

39 of 65 references.

References · 39

  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. 2017On Calibration of Modern Neural Networkscited by 4,860
  4. 2013Visualizing and Understanding Convolutional Networkscited by 2,278
  5. 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,543
  6. 2018A Survey Of Methods For Explaining Black Box Modelscited by 970
  7. 2018RISE: Randomized Input Sampling for Explanation of Black-box Modelscited by 825
  8. 2018Generative Image Inpainting with Contextual Attentioncited by 578
  9. 2020Neural Additive Models: Interpretable Machine Learning with Neural Netscited by 318
  10. 2020A Survey on Neural Network Interpretabilitycited by 291
  11. 2021On Explainability of Graph Neural Networks via Subgraph Explorationscited by 280
  12. 2020Opportunities and Challenges in Explainable Artificial Intelligence (XAI): A Surveycited by 252
27 more
  1. 2019InterpretML: A Unified Framework for Machine Learning Interpretabilitycited by 243
  2. 2020Explaining by Removing: A Unified Framework for Model Explanationcited by 218
  3. 2020GraphLIME: Local Interpretable Model Explanations for Graph Neural Networkscited by 209
  4. 2019Explaining individual predictions when features are dependent: More accurate approximations to Shapley valuescited by 205
  5. 2020Problems with Shapley-value-based explanations as feature importance measurescited by 198
  6. 2020Explainable Deep Learning: A Field Guide for the Uninitiatedcited by 127
  7. 2019Explaining Deep Neural Networks with a Polynomial Time Algorithm for Shapley Values Approximationcited by 115
  8. 2020Principles and Practice of Explainable Machine Learningcited by 99
  9. 2020On the Tractability of SHAP Explanationscited by 92
  10. 2020Explaining the Explainer: A First Theoretical Analysis of LIMEcited by 89
  11. 2021Explainability of deep vision-based autonomous driving systems: Review and challengescited by 80
  12. 2020TimeSHAP: Explaining Recurrent Models through Sequence Perturbationscited by 73
  13. 2020Interpretability and Explainability: A Machine Learning Zoo Mini-tourcited by 55
  14. 2020How Interpretable and Trustworthy are GAMs?cited by 44
  15. 2019ALIME: Autoencoder Based Approach for Local Interpretabilitycited by 41
  16. 2020SurvLIME: A method for explaining machine learning survival modelscited by 34
  17. 2019Explaining Anomalies Detected by Autoencoders Using SHAPcited by 27
  18. 2019Enriching Visual with Verbal Explanations for Relational Concepts -- Combining LIME with Alephcited by 23
  19. 2021The Shapley Value of Classifiers in Ensemble Gamescited by 23
  20. 2021What does LIME really see in images?cited by 21
  21. 2020Looking Deeper into Tabular LIMEcited by 20
  22. 2019Shapley Values of Reconstruction Errors of PCA for Explaining Anomaly Detectioncited by 19
  23. 2020Explaining predictive models with mixed features using Shapley values and conditional inference treescited by 18
  24. 2020Interpretable Machine Learning with an Ensemble of Gradient Boosting Machinescited by 14
  25. 2020Generalized SHAP: Generating multiple types of explanations in machine learningcited by 6
  26. 2020X-SHAP: towards multiplicative explainability of Machine Learningcited by 5
  27. 2020Explainable Empirical Risk Minimizationcited by 4

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 2; 2023: 3; 2024: 2.

8 papers.

  1. 2022WindowSHAP: An Efficient Framework for Explaining Time-series Classifiers based on Shapley Valuescited by 24
  2. 2021An Imprecise SHAP as a Tool for Explaining the Class Probability Distributions under Limited Training Datacited by 6
  3. 2023SurvBeX: An explanation method of the machine learning survival models based on the Beran estimatorcited by 3
  4. 2023Interpretable Ensembles of Hyper-Rectangles as Base Modelscited by 2
  5. 2024A survey and taxonomy of methods interpreting random forest modelscited by 2
  6. 2022An Explainable Stacked Ensemble Model for Static Route-Free Estimation of Time of Arrivalcited by 1
  7. 2023SurvBeNIM: The Beran-Based Neural Importance Model for Explaining the Survival Modelscited by 0
  8. 2024Dual feature-based and example-based explanation methodscited by 0