mlsanityData to 14 Oct 2026

On the Robustness of Global Feature Effect Explanations

arXiv 2406.09069 ↗First posted 13 Jun 2024cs.LG stat.MLcited by 2

Not on the map. Why?

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.

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

27 of 41 references.

References · 27

  1. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  2. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  3. 2018Sanity Checks for Saliency Mapscited by 1,156
  4. 2017Interpretation of Neural Networks is Fragilecited by 444
  5. 2019Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methodscited by 443
  6. 2018Lipschitz regularity of deep neural networks: analysis and efficient estimationcited by 415
  7. 2016Visualizing the Effects of Predictor Variables in Black Box Supervised Learning Modelscited by 213
  8. 2021Benchmarking and Survey of Explanation Methods for Black Box Modelscited by 136
  9. 2022OpenXAI: Towards a Transparent Evaluation of Model Explanationscited by 126
  10. 2021A Comprehensive Taxonomy for Explainable Artificial Intelligence: A Systematic Survey of Surveys on Methods and Conceptscited by 91
  11. 2018Visualizing the Feature Importance for Black Box Modelscited by 55
  12. 2018A Simple and Effective Model-Based Variable Importance Measurecited by 51
15 more
  1. 2023Adversarial attacks and defenses in explainable artificial intelligence: A surveycited by 48
  2. 2020Robust and Stable Black Box Explanationscited by 47
  3. 2022SAFARI: Versatile and Efficient Evaluations for Robustness of Interpretabilitycited by 28
  4. 2020The Grammar of Interactive Explanatory Model Analysiscited by 24
  5. 2021Relating the Partial Dependence Plot and Permutation Feature Importance to the Data Generating Processcited by 24
  6. 2022Robust Explanation Constraints for Neural Networkscited by 24
  7. 2023On the Robustness of Removal-Based Feature Attributionscited by 19
  8. 2022REPID: Regional Effect Plots with implicit Interaction Detectioncited by 17
  9. 2021Fooling Partial Dependence via Data Poisoningcited by 16
  10. 2023Generating robust counterfactual explanationscited by 13
  11. 2022DALE: Differential Accumulated Local Effects for efficient and accurate global explanationscited by 11
  12. 2023RHALE: Robust and Heterogeneity-aware Accumulated Local Effectscited by 8
  13. 2022"Is your explanation stable?": A Robustness Evaluation Framework for Feature Attributioncited by 7
  14. 2023iPDP: On Partial Dependence Plots in Dynamic Modeling Scenarioscited by 4
  15. 2023On Minimizing the Impact of Dataset Shifts on Actionable Explanationscited by 3

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 1.

2 papers.

  1. 2024Efficient and Accurate Explanation Estimation with Distribution Compressioncited by 4
  2. 2025Birds look like cars: Adversarial analysis of intrinsically interpretable deep learningcited by 3