# Statistical Significance of Feature Importance Rankings

arXiv: https://arxiv.org/abs/2401.15800 · HTML: https://mlsanity.com/paper/2401.15800/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 57 references that are in the map.
- First posted on arXiv 28 Jan 2024.

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

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Distribution-Free Predictive Inference For Regression](https://mlsanity.com/paper/1604.04173/) (2016)
- [Data Shapley: Equitable Valuation of Data for Machine Learning](https://mlsanity.com/paper/1904.02868/) (2019)
- [All Models are Wrong, but Many are Useful: Learning a Variable's Importance by Studying an Entire Class of Prediction Models Simultaneously](https://mlsanity.com/paper/1801.01489/) (2018)
- [Explaining individual predictions when features are dependent: More accurate approximations to Shapley values](https://mlsanity.com/paper/1903.10464/) (2019)
- [Improving KernelSHAP: Practical Shapley Value Estimation via Linear Regression](https://mlsanity.com/paper/2012.01536/) (2020)
- [Asymmetric Shapley values: incorporating causal knowledge into model-agnostic explainability](https://mlsanity.com/paper/1910.06358/) (2019)
- [Sampling Permutations for Shapley Value Estimation](https://mlsanity.com/paper/2104.12199/) (2021)
- [Principles and Practice of Explainable Machine Learning](https://mlsanity.com/paper/2009.11698/) (2020)
- [Neuron Shapley: Discovering the Responsible Neurons](https://mlsanity.com/paper/2002.09815/) (2020)
- [Unrestricted Permutation forces Extrapolation: Variable Importance Requires at least One More Model, or There Is No Free Variable Importance](https://mlsanity.com/paper/1905.03151/) (2019)
- [GTG-Shapley: Efficient and Accurate Participant Contribution Evaluation in Federated Learning](https://mlsanity.com/paper/2109.02053/) (2021)
- [Veridical Data Science](https://mlsanity.com/paper/1901.08152/) (2019)
- [S-LIME: Stabilized-LIME for Model Explanation](https://mlsanity.com/paper/2106.07875/) (2021)
- [Shapley Counterfactual Credits for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2106.00285/) (2021)
- [Global Aggregations of Local Explanations for Black Box models](https://mlsanity.com/paper/1907.03039/) (2019)
- [The Shapley Value of Classifiers in Ensemble Games](https://mlsanity.com/paper/2101.02153/) (2021)
- [Feature Importance: A Closer Look at Shapley Values and LOCO](https://mlsanity.com/paper/2303.05981/) (2023)
- [Rank Verification for Exponential Families](https://mlsanity.com/paper/1610.03944/) (2016)
- [Stabilizing Estimates of Shapley Values with Control Variates](https://mlsanity.com/paper/2310.07672/) (2023)
- [Crime Prediction Using Machine Learning and Deep Learning: A Systematic Review and Future Directions](https://mlsanity.com/paper/2303.16310/) (2023)
- [Confident Feature Ranking](https://mlsanity.com/paper/2307.15361/) (2023)
- [SHAP@k:Efficient and Probably Approximately Correct (PAC) Identification of Top-k Features](https://mlsanity.com/paper/2307.04850/) (2023)

## Built on by (most cited first, 7 of 7)

- [Feature Relevancy, Necessity and Usefulness: Complexity and Algorithms](https://mlsanity.com/paper/2505.09640/) (2025)
- [Top-k Feature Importance Ranking](https://mlsanity.com/paper/2509.15420/) (2025)
- [Unifying Image Counterfactuals and Feature Attributions with Latent-Space Adversarial Attacks](https://mlsanity.com/paper/2504.15479/) (2025)
- [Top-k on a Budget: Adaptive Ranking with Weak and Strong Oracles](https://mlsanity.com/paper/2601.20989/) (2026)
- [RoSHAP: A Distributional Framework and Robust Metric for Stable Feature Attribution](https://mlsanity.com/paper/2605.15154/) (2026)
- [K-IPO: Kendall-constrained Importance Preserving Oversampling for Imbalanced Tabular Data](https://mlsanity.com/paper/2607.16478/) (2026)
- [Measuring Explainer Stability via Attribution Separability](https://mlsanity.com/paper/2608.02697/) (2026)

## Abstract (arXiv)

Feature importance scores are ubiquitous tools for understanding the predictions of machine learning models. However, many popular attribution methods suffer from high instability due to random sampling. Leveraging novel ideas from hypothesis testing, we devise techniques that ensure the most important features are correct with high-probability guarantees. These assess the set of K top-ranked features, as well as the order of its elements. Given a set of local or global importance scores, we demonstrate how to retrospectively verify the stability of the highest ranks. We then introduce two efficient sampling algorithms that identify the K most important features, perhaps in order, with probability exceeding 1-α. The theoretical justification for these procedures is validated empirically on SHAP and LIME.