mlsanityData to 7 Oct 2026

A Survey on the Robustness of Feature Importance and Counterfactual Explanations

arXiv 2111.00358 ↗First posted 30 Oct 2021cs.LG cs.AIcited by 38

Not on the map. Why?

Abstract (arXiv)

There exist several methods that aim to address the crucial task of understanding the behaviour of AI/ML models. Arguably, the most popular among them are local explanations that focus on investigating model behaviour for individual instances. Several methods have been proposed for local analysis, but relatively lesser effort has gone into understanding if the explanations are robust and accurately reflect the behaviour of underlying models. In this work, we present a survey of the works that analysed the robustness of two classes of local explanations (feature importance and counterfactual explanations) that are popularly used in analysing AI/ML models in finance. The survey aims to unify existing definitions of robustness, introduces a taxonomy to classify different robustness approaches, and discusses some interesting results. Finally, the survey introduces some pointers about extending current robustness analysis approaches so as to identify reliable explainability methods.

Key facts. Cited by 38 papers in the map (data through 7 Oct 2026). Builds on 31 of its 42 references that are in the map. First posted on arXiv 30 Oct 2021.

Builds on

31 of 42 references.

References · 31

  1. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  2. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  3. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  4. 2018Sanity Checks for Saliency Mapscited by 1,149
  5. 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,086
  6. 2020Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?cited by 590
  7. 2018Explaining Explanations: An Overview of Interpretability of Machine Learningcited by 508
  8. 2017Interpretation of Neural Networks is Fragilecited by 443
  9. 2019Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methodscited by 440
  10. 2017Methods for Interpreting and Understanding Deep Neural Networkscited by 342
  11. 2017The (Un)reliability of saliency methodscited by 331
  12. 2018On the Robustness of Interpretability Methodscited by 310
19 more
  1. 2019FACE: Feasible and Actionable Counterfactual Explanationscited by 232
  2. 2019Explanations can be manipulated and geometry is to blamecited by 215
  3. 2020Evaluating and Aggregating Feature-based Model Explanationscited by 185
  4. 2020Multi-Objective Counterfactual Explanationscited by 157
  5. 2019Learning Model-Agnostic Counterfactual Explanations for Tabular Datacited by 146
  6. 2020A survey of algorithmic recourse: definitions, formulations, solutions, and prospectscited by 118
  7. 2021Counterfactual Explanations Can Be Manipulatedcited by 113
  8. 2019Fooling Neural Network Interpretations via Adversarial Model Manipulationcited by 112
  9. 2021Towards Robust and Reliable Algorithmic Recoursecited by 101
  10. 2019Benchmarking Attribution Methods with Relative Feature Importancecited by 89
  11. 2021CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithmscited by 85
  12. 2020Fairwashing Explanations with Off-Manifold Detergentcited by 71
  13. 2020Robust and Stable Black Box Explanationscited by 47
  14. 2020Towards Robust Explanations for Deep Neural Networkscited by 43
  15. 2019Evaluating Explanation Methods for Deep Learning in Securitycited by 38
  16. 2021Consistent Counterfactuals for Deep Modelscited by 37
  17. 2020Reliable Local Explanations for Machine Listeningcited by 17
  18. 2021A Causal Perspective on Meaningful and Robust Algorithmic Recoursecited by 8
  19. 2019"Why Should You Trust My Explanation?" Understanding Uncertainty in LIME Explanationscited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 7; 2023: 10; 2024: 11; 2025: 8; 2026: 2.

38 papers.

Sort:

By area:

  1. 2023Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directionscited by 123
  2. 2022Robust Counterfactual Explanations for Tree-Based Ensemblescited by 49
  3. 2022CLEAR: Generative Counterfactual Explanations on Graphscited by 48
  4. 2023Adversarial attacks and defenses in explainable artificial intelligence: A surveycited by 47
  5. 2023Robust Counterfactual Explanations for Neural Networks With Probabilistic Guaranteescited by 45
  6. 2024Robust Counterfactual Explanations in Machine Learning: A Surveycited by 29
  7. 2023GLOBE-CE: A Translation-Based Approach for Global Counterfactual Explanationscited by 27
  8. 2022Explainable AI for clinical and remote health applications: a survey on tabular and time series datacited by 24
  9. 2022Robust Bayesian Recoursecited by 18
  10. 2023Recourse under Model Multiplicity via Argumentative Ensembling (Technical Report)cited by 15
  11. 2023Generating robust counterfactual explanationscited by 13
  12. 2023Setting the Right Expectations: Algorithmic Recourse Over Timecited by 13
26 more
  1. 2023Robustness Implies Fairness in Causal Algorithmic Recoursecited by 12
  2. 2024Model Reconstruction Using Counterfactual Explanations: A Perspective From Polytope Theorycited by 12
  3. 2022RoCourseNet: Distributionally Robust Training of a Prediction Aware Recourse Modelcited by 11
  4. 2024Counterfactual Explanations with Probabilistic Guarantees on their Robustness to Model Changecited by 10
  5. 2024Fairness in Algorithmic Recourse Through the Lens of Substantive Equality of Opportunitycited by 9
  6. 2025Performative Validity of Recourse Explanationscited by 8
  7. 2024Interval Abstractions for Robust Counterfactual Explanationscited by 7
  8. 2024Counterfactual Metarules for Local and Global Recoursecited by 7
  9. 2023Confident Feature Rankingcited by 6
  10. 2024Why do explanations fail? A typology and discussion on failures in XAIcited by 6
  11. 2024When Can You Trust Your Explanations? A Robustness Analysis on Feature Importancescited by 5
  12. 2025Demystifying the Accuracy-Interpretability Trade-Off: A Case Study of Inferring Ratings from Reviewscited by 5
  13. 2025Counterfactual Explanations for Model Ensembles Using Entropic Risk Measurescited by 4
  14. 2022Robustness of Explanation Methods for NLP Modelscited by 3
  15. 2024The Effect of Data Poisoning on Counterfactual Explanationscited by 3
  16. 2025Few-Shot Knowledge Distillation of LLMs With Counterfactual Explanationscited by 3
  17. 2022RESHAPE: Explaining Accounting Anomalies in Financial Statement Audits by enhancing SHapley Additive exPlanationscited by 2
  18. 2024Generally-Occurring Model Change for Robust Counterfactual Explanationscited by 2
  19. 2023"How to make them stay?" -- Diverse Counterfactual Explanations of Employee Attritioncited by 1
  20. 2025Argumentative Ensembling for Robust Recourse under Model Multiplicitycited by 1
  21. 2025Synthesising Counterfactual Explanations via Label-Conditional Gaussian Mixture Variational Autoencoderscited by 1
  22. 2025CID: Measuring Feature Importance Through Counterfactual Distributionscited by 1
  23. 2024Private Counterfactual Retrieval With Immutable Featurescited by 0
  24. 2025What If, But Privately: Private Counterfactual Retrievalcited by 0
  25. 2026The Impact of Machine Learning Uncertainty on the Robustness of Counterfactual Explanationscited by 0
  26. 2026Structure-Aware Robust Counterfactual Explanations via Conditional Gaussian Network Classifierscited by 0