# On the Robustness of Global Feature Effect Explanations

arXiv: https://arxiv.org/abs/2406.09069 · HTML: https://mlsanity.com/paper/2406.09069/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 41 references that are in the map.
- First posted on arXiv 13 Jun 2024.

## Builds on (most cited first, 27 of 27)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [Interpretation of Neural Networks is Fragile](https://mlsanity.com/paper/1710.10547/) (2017)
- [Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods](https://mlsanity.com/paper/1911.02508/) (2019)
- [Lipschitz regularity of deep neural networks: analysis and efficient estimation](https://mlsanity.com/paper/1805.10965/) (2018)
- [Visualizing the Effects of Predictor Variables in Black Box Supervised Learning Models](https://mlsanity.com/paper/1612.08468/) (2016)
- [Benchmarking and Survey of Explanation Methods for Black Box Models](https://mlsanity.com/paper/2102.13076/) (2021)
- [OpenXAI: Towards a Transparent Evaluation of Model Explanations](https://mlsanity.com/paper/2206.11104/) (2022)
- [A Comprehensive Taxonomy for Explainable Artificial Intelligence: A Systematic Survey of Surveys on Methods and Concepts](https://mlsanity.com/paper/2105.07190/) (2021)
- [Visualizing the Feature Importance for Black Box Models](https://mlsanity.com/paper/1804.06620/) (2018)
- [A Simple and Effective Model-Based Variable Importance Measure](https://mlsanity.com/paper/1805.04755/) (2018)
- [Adversarial attacks and defenses in explainable artificial intelligence: A survey](https://mlsanity.com/paper/2306.06123/) (2023)
- [Robust and Stable Black Box Explanations](https://mlsanity.com/paper/2011.06169/) (2020)
- [SAFARI: Versatile and Efficient Evaluations for Robustness of Interpretability](https://mlsanity.com/paper/2208.09418/) (2022)
- [The Grammar of Interactive Explanatory Model Analysis](https://mlsanity.com/paper/2005.00497/) (2020)
- [Relating the Partial Dependence Plot and Permutation Feature Importance to the Data Generating Process](https://mlsanity.com/paper/2109.01433/) (2021)
- [Robust Explanation Constraints for Neural Networks](https://mlsanity.com/paper/2212.08507/) (2022)
- [On the Robustness of Removal-Based Feature Attributions](https://mlsanity.com/paper/2306.07462/) (2023)
- [REPID: Regional Effect Plots with implicit Interaction Detection](https://mlsanity.com/paper/2202.07254/) (2022)
- [Fooling Partial Dependence via Data Poisoning](https://mlsanity.com/paper/2105.12837/) (2021)
- [Generating robust counterfactual explanations](https://mlsanity.com/paper/2304.12943/) (2023)
- [DALE: Differential Accumulated Local Effects for efficient and accurate global explanations](https://mlsanity.com/paper/2210.04542/) (2022)
- [RHALE: Robust and Heterogeneity-aware Accumulated Local Effects](https://mlsanity.com/paper/2309.11193/) (2023)
- ["Is your explanation stable?": A Robustness Evaluation Framework for Feature Attribution](https://mlsanity.com/paper/2209.01782/) (2022)
- [iPDP: On Partial Dependence Plots in Dynamic Modeling Scenarios](https://mlsanity.com/paper/2306.07775/) (2023)
- [On Minimizing the Impact of Dataset Shifts on Actionable Explanations](https://mlsanity.com/paper/2306.06716/) (2023)

## Built on by (most cited first, 2 of 2)

- [Efficient and Accurate Explanation Estimation with Distribution Compression](https://mlsanity.com/paper/2406.18334/) (2024)
- [Birds look like cars: Adversarial analysis of intrinsically interpretable deep learning](https://mlsanity.com/paper/2503.08636/) (2025)

## Abstract (arXiv)

We study the robustness of global post-hoc explanations for predictive models trained on tabular data. Effects of predictor features in black-box supervised learning are an essential diagnostic tool for model debugging and scientific discovery in applied sciences. However, how vulnerable they are to data and model perturbations remains an open research question. We introduce several theoretical bounds for evaluating the robustness of partial dependence plots and accumulated local effects. Our experimental results with synthetic and real-world datasets quantify the gap between the best and worst-case scenarios of (mis)interpreting machine learning predictions globally.