Energy-Based Model for Accurate Estimation of Shapley Values in Feature Attribution
Not on the map. Why?
Abstract (arXiv)
Shapley value is a widely used tool in explainable artificial intelligence (XAI), as it provides a principled way to attribute contributions of input features to model outputs. However, estimation of Shapley value requires capturing conditional dependencies among all feature combinations, which poses significant challenges in complex data environments. In this article, EmSHAP (Energy-based model for Shapley value estimation), an accurate Shapley value estimation method, is proposed to estimate the expectation of Shapley contribution function under the arbitrary subset of features given the rest. By utilizing the ability of energy-based model (EBM) to model complex distributions, EmSHAP provides an effective solution for estimating the required conditional probabilities. To further improve estimation accuracy, a GRU (Gated Recurrent Unit)-coupled partition function estimation method is introduced. The GRU network captures long-term dependencies with a lightweight parameterization and maps input features into a latent space to mitigate the influence of feature ordering. Additionally, a dynamic masking mechanism is incorporated to further enhance the robustness and accuracy by progressively increasing the masking rate. Theoretical analysis on the error bound as well as application to four case studies verified the higher accuracy and better scalability of EmSHAP in contrast to competitive methods.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 48 of its 79 references that are in the map. First posted on arXiv 1 Apr 2024.
Builds on
48 of 79 references.
References · 48
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2014Explaining and Harnessing Adversarial Examplescited by 7,287
- 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
- 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,141
- 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,543
- 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,400
- 2014Convolutional Neural Networks for Sentence Classificationcited by 1,124
- 2019Your Classifier is Secretly an Energy Based Model and You Should Treat it Like Onecited by 402
- 2019The many Shapley values for model explanationcited by 341
- 2018Explainable Prediction of Medical Codes from Clinical Textcited by 231
- 2020Problems with Shapley-value-based explanations as feature importance measurescited by 198
- 2020Improving KernelSHAP: Practical Shapley Value Estimation via Linear Regressioncited by 153
36 more
- 2018Inference Suboptimality in Variational Autoencoderscited by 131
- 2021FastSHAP: Real-Time Shapley Value Estimationcited by 123
- 2019XRAI: Better Attributions Through Regionscited by 116
- 2019Explaining Deep Neural Networks with a Polynomial Time Algorithm for Shapley Values Approximationcited by 115
- 2022Algorithms to estimate Shapley value feature attributionscited by 114
- 2016Deep Structured Energy Based Models for Anomaly Detectioncited by 113
- 2020ICE-BeeM: Identifiable Conditional Energy-Based Deep Models Based on Nonlinear ICAcited by 102
- 2021Sampling Permutations for Shapley Value Estimationcited by 101
- 2018L-Shapley and C-Shapley: Efficient Model Interpretation for Structured Datacited by 100
- 2020Deep Learning for Financial Applications : A Surveycited by 90
- 2020Explaining the Explainer: A First Theoretical Analysis of LIMEcited by 89
- 2020Shapley explainability on the data manifoldcited by 88
- 2020Generalized Energy Based Modelscited by 73
- 2022Faith-Shap: The Faithful Shapley Interaction Indexcited by 68
- 2020Efficient nonparametric statistical inference on population feature importance using Shapley valuescited by 61
- 2022From Shapley Values to Generalized Additive Models and backcited by 59
- 2021Shapley values for feature selection: The good, the bad, and the axiomscited by 54
- 2023SHAP-IQ: Unified Approximation of any-order Shapley Interactionscited by 50
- 2023Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Studycited by 48
- 2022Heterogeneous Graph Masked Autoencoderscited by 47
- 2021Shapley Explanation Networkscited by 41
- 2019FastGRNN: A Fast, Accurate, Stable and Tiny Kilobyte Sized Gated Recurrent Neural Networkcited by 38
- 2021Explaining a Series of Models by Propagating Shapley Valuescited by 37
- 2023Approximating the Shapley Value without Marginal Contributionscited by 34
- 2020A Multilinear Sampling Algorithm to Estimate Shapley Valuescited by 33
- 2021RKHS-SHAP: Shapley Values for Kernel Methodscited by 30
- 2024Beyond TreeSHAP: Efficient Computation of Any-Order Shapley Interactions for Tree Ensemblescited by 30
- 2019Autoregressive Energy Machinescited by 23
- 2023Feature Importance: A Closer Look at Shapley Values and LOCOcited by 23
- 2021Arbitrary Conditional Distributions with Energycited by 22
- 2021Using Shapley Values and Variational Autoencoders to Explain Predictive Models with Dependent Mixed Featurescited by 19
- 2024SVARM-IQ: Efficient Approximation of Any-order Shapley Interactions through Stratificationcited by 16
- 2021VAE Approximation Error: ELBO and Exponential Familiescited by 12
- 2021Identifiable Energy-based Representations: An Application to Estimating Heterogeneous Causal Effectscited by 7
- 2023Shaping Up SHAP: Enhancing Stability through Layer-Wise Neighbor Selectioncited by 7
- 2023A feature selection method based on Shapley values robust to concept shift in regressioncited by 6
Built on by
Citing papers per year: 2025: 1.
1 paper.