mlsanityData to 7 Oct 2026

Prediction via Shapley Value Regression

arXiv 2505.04775 ↗First posted 7 May 2025cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

Shapley values have several desirable, theoretically well-supported, properties for explaining black-box model predictions. Traditionally, Shapley values are computed post-hoc, leading to additional computational cost at inference time. To overcome this, a novel method, called ViaSHAP, is proposed, that learns a function to compute Shapley values, from which the predictions can be derived directly by summation. Two approaches to implement the proposed method are explored; one based on the universal approximation theorem and the other on the Kolmogorov-Arnold representation theorem. Results from a large-scale empirical investigation are presented, showing that ViaSHAP using Kolmogorov-Arnold Networks performs on par with state-of-the-art algorithms for tabular data. It is also shown that the explanations of ViaSHAP are significantly more accurate than the popular approximator FastSHAP on both tabular data and images.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 43 of its 64 references that are in the map. First posted on arXiv 7 May 2025.

Builds on

43 of 64 references.

References · 43

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  4. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  5. 2019TabNet: Attentive Interpretable Tabular Learningcited by 640
  6. 2019Explaining Machine Learning Classifiers through Diverse Counterfactual Explanationscited by 612
  7. 2021Tabular Data: Deep Learning is Not All You Needcited by 530
  8. 2018Towards Robust Interpretability with Self-Explaining Neural Networkscited by 505
  9. 2016European Union regulations on algorithmic decision-making and a "right to explanation"cited by 343
  10. 2019The many Shapley values for model explanationcited by 341
  11. 2016Rationalizing Neural Predictionscited by 281
  12. 2018Learning to Explain: An Information-Theoretic Perspective on Model Interpretationcited by 248
31 more
  1. 2019Interpretable Counterfactual Explanations Guided by Prototypescited by 223
  2. 2020Explaining by Removing: A Unified Framework for Model Explanationcited by 218
  3. 2019Explaining individual predictions when features are dependent: More accurate approximations to Shapley valuescited by 205
  4. 2019Model-Agnostic Counterfactual Explanations for Consequential Decisionscited by 204
  5. 2020Multi-Objective Counterfactual Explanationscited by 157
  6. 2020Improving KernelSHAP: Practical Shapley Value Estimation via Linear Regressioncited by 153
  7. 2020True to the Model or True to the Data?cited by 123
  8. 2019Explaining Deep Neural Networks with a Polynomial Time Algorithm for Shapley Values Approximationcited by 115
  9. 2022Algorithms to estimate Shapley value feature attributionscited by 114
  10. 2021Sampling Permutations for Shapley Value Estimationcited by 101
  11. 2018L-Shapley and C-Shapley: Efficient Model Interpretation for Structured Datacited by 100
  12. 2019CXPlain: Causal Explanations for Model Interpretation under Uncertaintycited by 98
  13. 2020Shapley explainability on the data manifoldcited by 88
  14. 2022Concept Bottleneck Model with Additional Unsupervised Conceptscited by 79
  15. 2021Towards Self-Explainable Graph Neural Networkcited by 75
  16. 2021Have We Learned to Explain?: How Interpretability Methods Can Learn to Encode Predictions in their Interpretationscited by 59
  17. 2022Interpretable Graph Neural Networks for Connectome-Based Brain Disorder Analysiscited by 58
  18. 2017Interpretable & Explorable Approximations of Black Box Modelscited by 54
  19. 2022KerGNNs: Interpretable Graph Neural Networks with Graph Kernelscited by 50
  20. 2021Shapley Explanation Networkscited by 41
  21. 2023Approximating the Shapley Value without Marginal Contributionscited by 34
  22. 2022Global Concept-Based Interpretability for Graph Neural Networks via Neuron Analysiscited by 32
  23. 2017Contextual Explanation Networkscited by 21
  24. 2022VCNet: A self-explaining model for realistic counterfactual generationcited by 20
  25. 2023HarsanyiNet: Computing Accurate Shapley Values in a Single Forward Propagationcited by 16
  26. 2021Fast Hierarchical Games for Image Explanationscited by 15
  27. 2020High Dimensional Model Explanations: an Axiomatic Approachcited by 13
  28. 2020A Baseline for Shapley Values in MLPs: from Missingness to Neutralitycited by 11
  29. 2023Interpretable Graph Neural Networks for Tabular Datacited by 5
  30. 2025Explaining Vision GNNs: A Semantic and Visual Analysis of Graph-based Image Classificationcited by 2
  31. 2024Interpretable Graph Neural Networks for Heterogeneous Tabular Datacited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2026Uncertainty-Aware Multimodal Learning via Conformal Shapley Intervalscited by 1
  2. 2025Transferring Visual Explainability of Self-Explaining Models to Prediction-Only Models without Additional Trainingcited by 0
  3. 2026Real-Time Explanations for Tabular Foundation Modelscited by 0