# Shapley values for feature selection: The good, the bad, and the axioms

arXiv: https://arxiv.org/abs/2102.10936 · HTML: https://mlsanity.com/paper/2102.10936/

## Key facts

- Cited by 54 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 54 references that are in the map.
- First posted on arXiv 22 Feb 2021.

## Builds on (most cited first, 15 of 15)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [The many Shapley values for model explanation](https://mlsanity.com/paper/1908.08474/) (2019)
- [Consistent Individualized Feature Attribution for Tree Ensembles](https://mlsanity.com/paper/1802.03888/) (2018)
- [Explaining by Removing: A Unified Framework for Model Explanation](https://mlsanity.com/paper/2011.14878/) (2020)
- [Explaining individual predictions when features are dependent: More accurate approximations to Shapley values](https://mlsanity.com/paper/1903.10464/) (2019)
- [Problems with Shapley-value-based explanations as feature importance measures](https://mlsanity.com/paper/2002.11097/) (2020)
- [Asymmetric Shapley values: incorporating causal knowledge into model-agnostic explainability](https://mlsanity.com/paper/1910.06358/) (2019)
- [Explainable AI for Trees: From Local Explanations to Global Understanding](https://mlsanity.com/paper/1905.04610/) (2019)
- [Efficient computation and analysis of distributional Shapley values](https://mlsanity.com/paper/2007.01357/) (2020)
- [Explaining predictive models with mixed features using Shapley values and conditional inference trees](https://mlsanity.com/paper/2007.01027/) (2020)
- [Predictive and Causal Implications of using Shapley Value for Model Interpretation](https://mlsanity.com/paper/2008.05052/) (2020)
- [The Explanation Game: Explaining Machine Learning Models Using Shapley Values](https://mlsanity.com/paper/1909.08128/) (2019)
- [A Feature Selection Method Based on Shapley Value to False Alarm Reduction in ICUs, A Genetic-Algorithm Approach](https://mlsanity.com/paper/1804.11196/) (2018)
- [Explaining the data or explaining a model? Shapley values that uncover non-linear dependencies](https://mlsanity.com/paper/2007.06011/) (2020)
- [Interpretable feature subset selection: A Shapley value based approach](https://mlsanity.com/paper/2001.03956/) (2020)

## Built on by (most cited first, 30 of 54)

- [AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers](https://mlsanity.com/paper/2402.05602/) (2024)
- [The Shapley Value in Machine Learning](https://mlsanity.com/paper/2202.05594/) (2022)
- [Explainable AI for Safe and Trustworthy Autonomous Driving: A Systematic Review](https://mlsanity.com/paper/2402.10086/) (2024)
- [The Inadequacy of Shapley Values for Explainability](https://mlsanity.com/paper/2302.08160/) (2023)
- [To trust or not to trust an explanation: using LEAF to evaluate local linear XAI methods](https://mlsanity.com/paper/2106.00461/) (2021)
- [Provably Accurate Shapley Value Estimation via Leverage Score Sampling](https://mlsanity.com/paper/2410.01917/) (2024)
- [Using Shapley Values and Variational Autoencoders to Explain Predictive Models with Dependent Mixed Features](https://mlsanity.com/paper/2111.13507/) (2021)
- [A Comparative Study of Methods for Estimating Conditional Shapley Values and When to Use Them](https://mlsanity.com/paper/2305.09536/) (2023)
- [Analyzing the Role of Semantic Representations in the Era of Large Language Models](https://mlsanity.com/paper/2405.01502/) (2024)
- [SyntaxShap: Syntax-aware Explainability Method for Text Generation](https://mlsanity.com/paper/2402.09259/) (2024)
- [New Definitions and Evaluations for Saliency Methods: Staying Intrinsic, Complete and Sound](https://mlsanity.com/paper/2211.02912/) (2022)
- [Prompt Valuation Based on Shapley Values](https://mlsanity.com/paper/2312.15395/) (2023)
- [ROSE: A Reward-Oriented Data Selection Framework for LLM Task-Specific Instruction Tuning](https://mlsanity.com/paper/2412.00631/) (2024)
- [INTER: Mitigating Hallucination in Large Vision-Language Models by Interaction Guidance Sampling](https://mlsanity.com/paper/2507.05056/) (2025)
- [Differentially Private Shapley Values for Data Evaluation](https://mlsanity.com/paper/2206.00511/) (2022)
- [SHAP Meets Tensor Networks: Provably Tractable Explanations with Parallelism](https://mlsanity.com/paper/2510.21599/) (2025)
- [SHAP-XRT: The Shapley Value Meets Conditional Independence Testing](https://mlsanity.com/paper/2207.07038/) (2022)
- [Revisiting LRP: Positional Attribution as the Missing Ingredient for Transformer Explainability](https://mlsanity.com/paper/2506.02138/) (2025)
- [Explainability of Machine Learning Models under Missing Data](https://mlsanity.com/paper/2407.00411/) (2024)
- [A Scalable, Interpretable, Verifiable & Differentiable Logic Gate Convolutional Neural Network Architecture From Truth Tables](https://mlsanity.com/paper/2208.08609/) (2022)
- [Predicting Dynamic Stability from Static Features in Power Grid Models using Machine Learning](https://mlsanity.com/paper/2210.09266/) (2022)
- [A Refutation of Shapley Values for Explainability](https://mlsanity.com/paper/2309.03041/) (2023)
- [Local Interpretable Model Agnostic Shap Explanations for machine learning models](https://mlsanity.com/paper/2210.04533/) (2022)
- [Quantifying Genuine Awareness in Hallucination Prediction Beyond Question-Side Shortcuts](https://mlsanity.com/paper/2509.15339/) (2025)
- [Inferring feature importance with uncertainties in high-dimensional data](https://mlsanity.com/paper/2109.00855/) (2021)
- [Shapley Based Residual Decomposition for Instance Analysis](https://mlsanity.com/paper/2305.18818/) (2023)
- [Beyond Single-Feature Importance with ICECREAM](https://mlsanity.com/paper/2307.09779/) (2023)
- [Explainable AI for survival analysis: a median-SHAP approach](https://mlsanity.com/paper/2402.00072/) (2024)
- [A Comprehensive Study of Shapley Value in Data Analytics](https://mlsanity.com/paper/2412.01460/) (2024)
- [From Pixels to Perception: Interpretable Predictions via Instance-wise Grouped Feature Selection](https://mlsanity.com/paper/2505.06003/) (2025)

## Abstract (arXiv)

The Shapley value has become popular in the Explainable AI (XAI) literature, thanks, to a large extent, to a solid theoretical foundation, including four "favourable and fair" axioms for attribution in transferable utility games. The Shapley value is provably the only solution concept satisfying these axioms. In this paper, we introduce the Shapley value and draw attention to its recent uses as a feature selection tool. We call into question this use of the Shapley value, using simple, abstract "toy" counterexamples to illustrate that the axioms may work against the goals of feature selection. From this, we develop a number of insights that are then investigated in concrete simulation settings, with a variety of Shapley value formulations, including SHapley Additive exPlanations (SHAP) and Shapley Additive Global importancE (SAGE).