mlsanityData to 14 Oct 2026

Using Shapley Values and Variational Autoencoders to Explain Predictive Models with Dependent Mixed Features

arXiv 2111.13507 ↗First posted 26 Nov 2021stat.ML cs.LGcited by 19

Not on the map. Why?

Abstract (arXiv)

Shapley values are today extensively used as a model-agnostic explanation framework to explain complex predictive machine learning models. Shapley values have desirable theoretical properties and a sound mathematical foundation in the field of cooperative game theory. Precise Shapley value estimates for dependent data rely on accurate modeling of the dependencies between all feature combinations. In this paper, we use a variational autoencoder with arbitrary conditioning (VAEAC) to model all feature dependencies simultaneously. We demonstrate through comprehensive simulation studies that our VAEAC approach to Shapley value estimation outperforms the state-of-the-art methods for a wide range of settings for both continuous and mixed dependent features. For high-dimensional settings, our VAEAC approach with a non-uniform masking scheme significantly outperforms competing methods. Finally, we apply our VAEAC approach to estimate Shapley value explanations for the Abalone data set from the UCI Machine Learning Repository.

Key facts. Cited by 19 papers in the map (data through 14 Oct 2026). Builds on 37 of its 95 references that are in the map. First posted on arXiv 26 Nov 2021.

Builds on

37 of 95 references.

References · 37

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  5. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  6. 2016Densely Connected Convolutional Networkscited by 6,720
  7. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  8. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  9. 2016Variational Inference: A Review for Statisticianscited by 1,472
  10. 2017Visualizing the Loss Landscape of Neural Netscited by 1,130
  11. 2019An Introduction to Variational Autoencoderscited by 1,000
  12. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 776
25 more
  1. 2015Generating Sentences from a Continuous Spacecited by 612
  2. 2018GAIN: Missing Data Imputation using Generative Adversarial Netscited by 352
  3. 2018Consistent Individualized Feature Attribution for Tree Ensemblescited by 285
  4. 2020Explaining by Removing: A Unified Framework for Model Explanationcited by 218
  5. 2019Explaining individual predictions when features are dependent: More accurate approximations to Shapley valuescited by 208
  6. 2015ranger: A Fast Implementation of Random Forests for High Dimensional Data in C++ and Rcited by 172
  7. 2018A Hierarchical Latent Vector Model for Learning Long-Term Structure in Musiccited by 131
  8. 2020True to the Model or True to the Data?cited by 126
  9. 2019Asymmetric Shapley values: incorporating causal knowledge into model-agnostic explainabilitycited by 114
  10. 2020Causal Shapley Values: Exploiting Causal Knowledge to Explain Individual Predictions of Complex Modelscited by 107
  11. 2021Sampling Permutations for Shapley Value Estimationcited by 102
  12. 2020Shapley explainability on the data manifoldcited by 88
  13. 2018Variational Autoencoder with Arbitrary Conditioningcited by 68
  14. 2020Efficient nonparametric statistical inference on population feature importance using Shapley valuescited by 61
  15. 2021Shapley values for feature selection: The good, the bad, and the axiomscited by 54
  16. 2021groupShapley: Efficient prediction explanation with Shapley values for feature groupscited by 21
  17. 2020Explaining predictive models with mixed features using Shapley values and conditional inference treescited by 18
  18. 2017CosmoGAN: creating high-fidelity weak lensing convergence maps using Generative Adversarial Networkscited by 17
  19. 2021Joint Shapley values: a measure of joint feature importancecited by 15
  20. 2017A Universal Marginalizer for Amortized Inference in Generative Modelscited by 9
  21. 2021Explaining predictive models using Shapley values and non-parametric vine copulascited by 9
  22. 2018Learning a Latent Space of Multitrack Measurescited by 8
  23. 2018Prediction based on conditional distributions of vine copulascited by 8
  24. 2019A hybrid machine learning framework for analyzing human decision making through learning preferencescited by 4
  25. 2020Masking schemes for universal marginaliserscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 2; 2023: 4; 2024: 9; 2025: 2; 2026: 2.

19 papers.

Sort:

  1. 2022Algorithms to estimate Shapley value feature attributionscited by 115
  2. 2024shapiq: Shapley Interactions for Machine Learningcited by 43
  3. 2023Explaining Predictive Uncertainty with Information Theoretic Shapley Valuescited by 36
  4. 2024Decoupling Pixel Flipping and Occlusion Strategy for Consistent XAI Benchmarkscited by 28
  5. 2022SurvSHAP(t): Time-dependent explanations of machine learning survival modelscited by 24
  6. 2023A Comparative Study of Methods for Estimating Conditional Shapley Values and When to Use Themcited by 15
  7. 2024Improving the Weighting Strategy in KernelSHAPcited by 5
  8. 2025shapr: Explaining Machine Learning Models with Conditional Shapley Values in R and Pythoncited by 5
  9. 2024Interpretable Machine Learning for Survival Analysiscited by 4
  10. 2024Efficient and Accurate Explanation Estimation with Distribution Compressioncited by 4
  11. 2023Approximation of group explainers with coalition structure using Monte Carlo sampling on the product space of coalitions and featurescited by 2
  12. 2024A Comprehensive Study of Shapley Value in Data Analyticscited by 2
7 more
  1. 2023Precision of Individual Shapley Value Explanationscited by 1
  2. 2024Energy-Based Model for Accurate Estimation of Shapley Values in Feature Attributioncited by 1
  3. 2025Interaction Tensor SHAPcited by 1
  4. 2026Computing Conditional Shapley Values Using Tabular Foundation Modelscited by 1
  5. 2026Functional Decomposition and Shapley Interactions for Interpreting Survival Modelscited by 1
  6. 2024Explain Variance of Prediction in Variational Time Series Models for Clinical Deterioration Predictioncited by 0
  7. 2024On the influence of dependent features in classification problems: a game-theoretic perspectivecited by 0