# MinShap: A Shapley-Based Framework for Feature Redundancy

arXiv: https://arxiv.org/abs/2604.15107 · HTML: https://mlsanity.com/paper/2604.15107/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 62 references that are in the map.
- First posted on arXiv 16 Apr 2026.

## Builds on (most cited first, 24 of 24)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small](https://mlsanity.com/paper/2211.00593/) (2022)
- [Distribution-Free Predictive Inference For Regression](https://mlsanity.com/paper/1604.04173/) (2016)
- [AI Feynman: a Physics-Inspired Method for Symbolic Regression](https://mlsanity.com/paper/1905.11481/) (2019)
- [The many Shapley values for model explanation](https://mlsanity.com/paper/1908.08474/) (2019)
- [Causal Discovery with Continuous Additive Noise Models](https://mlsanity.com/paper/1309.6779/) (2013)
- [Problems with Shapley-value-based explanations as feature importance measures](https://mlsanity.com/paper/2002.11097/) (2020)
- [Feature relevance quantification in explainable AI: A causal problem](https://mlsanity.com/paper/1910.13413/) (2019)
- [Algorithms to estimate Shapley value feature attributions](https://mlsanity.com/paper/2207.07605/) (2022)
- [The Shapley Value in Machine Learning](https://mlsanity.com/paper/2202.05594/) (2022)
- [Efficient nonparametric statistical inference on population feature importance using Shapley values](https://mlsanity.com/paper/2006.09481/) (2020)
- [Shapley values for feature selection: The good, the bad, and the axioms](https://mlsanity.com/paper/2102.10936/) (2021)
- [A general framework for inference on algorithm-agnostic variable importance](https://mlsanity.com/paper/2004.03683/) (2020)
- [Relating the Partial Dependence Plot and Permutation Feature Importance to the Data Generating Process](https://mlsanity.com/paper/2109.01433/) (2021)
- [Predictive and Causal Implications of using Shapley Value for Model Interpretation](https://mlsanity.com/paper/2008.05052/) (2020)
- [Decorrelated Variable Importance](https://mlsanity.com/paper/2111.10853/) (2021)
- [Conditional independence testing under misspecified inductive biases](https://mlsanity.com/paper/2307.02520/) (2023)
- [SHAP-XRT: The Shapley Value Meets Conditional Independence Testing](https://mlsanity.com/paper/2207.07038/) (2022)
- [Lazy Estimation of Variable Importance for Large Neural Networks](https://mlsanity.com/paper/2207.09097/) (2022)
- [Computing Shapley Effects for Sensitivity Analysis](https://mlsanity.com/paper/2002.12024/) (2020)
- [Interpretable feature subset selection: A Shapley value based approach](https://mlsanity.com/paper/2001.03956/) (2020)
- [Feature Relevancy, Necessity and Usefulness: Complexity and Algorithms](https://mlsanity.com/paper/2505.09640/) (2025)

## Built on by (most cited first, 1 of 1)

- [Null importance: Disentangling relevance for interpretable machine learning](https://mlsanity.com/paper/2609.19511/) (2026)

## Abstract (arXiv)

Shapley values provide a flexible framework for attributing feature contributions to model predictions, but they are not naturally suited for feature selection: a feature may receive a positive attribution even when it is redundant given the remaining variables. In this paper, we introduce MinShap, a general framework for identifying important or non-redundant features through conditional importance functionals VIjS. Rather than averaging feature contributions across conditioning sets, MinShap aggregates them using the minimum, thereby testing whether a feature remains relevant under every conditioning context. We show that, under a simple null monotonicity condition, the minimum aggregation exactly characterizes feature redundancy and yields a principled feature selection criterion. This perspective provides a unified framework for statistical feature selection and representation-based interpretability while retaining the stability advantages of Shapley-style aggregation. We develop scalable algorithms with statistical guarantees, establish connections to multiple-testing procedures, and demonstrate through theory and experiments that MinShap produces more accurate and stable feature selection than existing model-agnostic approaches.