mlsanityData to 14 Oct 2026

Seven challenges for harmonizing explainability requirements

arXiv 2108.05390 ↗First posted 11 Aug 2021cs.LG cs.AI cs.CYcited by 4

Not on the map. Why?

Abstract (arXiv)

Regulators have signalled an interest in adopting explainable AI(XAI) techniques to handle the diverse needs for model governance, operational servicing, and compliance in the financial services industry. In this short overview, we review the recent technical literature in XAI and argue that based on our current understanding of the field, the use of XAI techniques in practice necessitate a highly contextualized approach considering the specific needs of stakeholders for particular business applications.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 54 of its 98 references that are in the map. First posted on arXiv 11 Aug 2021.

Builds on

54 of 98 references.

References · 54

  1. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  4. 2017Explanation in Artificial Intelligence: Insights from the Social Sciencescited by 1,206
  5. 2020A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challengescited by 819
  6. 2019Explaining Machine Learning Classifiers through Diverse Counterfactual Explanationscited by 614
  7. 2018Certified Robustness to Adversarial Examples with Differential Privacycited by 468
  8. 2019Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methodscited by 443
  9. 2019The many Shapley values for model explanationcited by 344
  10. 2017The (Un)reliability of saliency methodscited by 333
  11. 2018Actionable Recourse in Linear Classificationcited by 328
  12. 2018On the Robustness of Interpretability Methodscited by 314
38 more
  1. 2018Consistent Individualized Feature Attribution for Tree Ensemblescited by 285
  2. 2020Influence Functions in Deep Learning Are Fragilecited by 252
  3. 2020Algorithmic Recourse: from Counterfactual Explanations to Interventionscited by 250
  4. 2018Explainable Prediction of Medical Codes from Clinical Textcited by 234
  5. 2019Explanations can be manipulated and geometry is to blamecited by 216
  6. 2018Explainable Recommendation: A Survey and New Perspectivescited by 210
  7. 2020Problems with Shapley-value-based explanations as feature importance measurescited by 200
  8. 2020Fast and Complete: Enabling Complete Neural Network Verification with Rapid and Massively Parallel Incomplete Verifierscited by 187
  9. 2019Anti-Money Laundering in Bitcoin: Experimenting with Graph Convolutional Networks for Financial Forensicscited by 164
  10. 2018Explaining Explanations in AIcited by 137
  11. 2020Explainable Deep Learning: A Field Guide for the Uninitiatedcited by 127
  12. 2020True to the Model or True to the Data?cited by 126
  13. 2021Expanding Explainability: Towards Social Transparency in AI systemscited by 124
  14. 2019Asymmetric Shapley values: incorporating causal knowledge into model-agnostic explainabilitycited by 114
  15. 2020Human-centered Explainable AI: Towards a Reflective Sociotechnical Approachcited by 90
  16. 2018Model Agnostic Supervised Local Explanationscited by 83
  17. 2019Fairwashing: the risk of rationalizationcited by 81
  18. 2020Fairwashing Explanations with Off-Manifold Detergentcited by 72
  19. 2018Explanation Methods in Deep Learning: Users, Values, Concerns and Challengescited by 49
  20. 2021Exploiting Explanations for Model Inversion Attackscited by 49
  21. 2018Interpretable to Whom? A Role-based Model for Analyzing Interpretable Machine Learning Systemscited by 48
  22. 2020Model extraction from counterfactual explanationscited by 47
  23. 2021Order in the Court: Explainable AI Methods Prone to Disagreementcited by 36
  24. 2019On the computation of counterfactual explanations -- A surveycited by 33
  25. 2019Measuring the Business Value of Recommender Systemscited by 32
  26. 2018POTs: Protective Optimization Technologiescited by 28
  27. 2021Where and What? Examining Interpretable Disentangled Representationscited by 27
  28. 2020Causality-based Explanation of Classification Outcomescited by 25
  29. 2020Machine Learning Explainability for External Stakeholderscited by 17
  30. 2019Towards Explainable AI Planning as a Servicecited by 14
  31. 2020Uncertainty Quantification for Sparse Deep Learningcited by 13
  32. 2021SummVis: Interactive Visual Analysis of Models, Data, and Evaluation for Text Summarizationcited by 13
  33. 2018Fair lending needs explainable models for responsible recommendationcited by 12
  34. 2020Distal Explanations for Model-free Explainable Reinforcement Learningcited by 12
  35. 2020Bias in Data-driven AI Systems -- An Introductory Surveycited by 10
  36. 2021Model Learning with Personalized Interpretability Estimation (ML-PIE)cited by 9
  37. 2019Learning Interpretable Disentangled Representations using Adversarial VAEscited by 8
  38. 2020Towards Self-Regulating AI: Challenges and Opportunities of AI Model Governance in Financial Servicescited by 8

50 most cited of 54 All 54 (JSON)

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 2.

4 papers.

  1. 2022Monotonic Neural Additive Models: Pursuing Regulated Machine Learning Models for Credit Scoringcited by 12
  2. 2022Explainability in reinforcement learning: perspective and positioncited by 11
  3. 2023A Comprehensive Review on Financial Explainable AIcited by 10
  4. 2023Five policy uses of algorithmic transparency and explainabilitycited by 0