mlsanityData to 14 Oct 2026

Marrying Fairness and Explainability in Supervised Learning

arXiv 2204.02947 ↗First posted 6 Apr 2022cs.LG cs.CYcited by 23

Not on the map. Why?

Abstract (arXiv)

Machine learning algorithms that aid human decision-making may inadvertently discriminate against certain protected groups. We formalize direct discrimination as a direct causal effect of the protected attributes on the decisions, while induced discrimination as a change in the causal influence of non-protected features associated with the protected attributes. The measurements of marginal direct effect (MDE) and SHapley Additive exPlanations (SHAP) reveal that state-of-the-art fair learning methods can induce discrimination via association or reverse discrimination in synthetic and real-world datasets. To inhibit discrimination in algorithmic systems, we propose to nullify the influence of the protected attribute on the output of the system, while preserving the influence of remaining features. We introduce and study post-processing methods achieving such objectives, finding that they yield relatively high model accuracy, prevent direct discrimination, and diminishes various disparity measures, e.g., demographic disparity.

Key facts. Cited by 23 papers in the map (data through 14 Oct 2026). Builds on 34 of its 74 references that are in the map. First posted on arXiv 6 Apr 2022.

Builds on

34 of 74 references.

References · 34

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  4. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  5. 2016Equality of Opportunity in Supervised Learningcited by 2,007
  6. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,375
  7. 2017Counterfactual Fairnesscited by 804
  8. 2014Certifying and removing disparate impactcited by 715
  9. 2016Fair prediction with disparate impact: A study of bias in recidivism prediction instrumentscited by 672
  10. 2018Mitigating Unwanted Biases with Adversarial Learningcited by 663
  11. 2018A Reductions Approach to Fair Classificationcited by 587
  12. 2016Inherent Trade-Offs in the Fair Determination of Risk Scorescited by 586
22 more
  1. 2019Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methodscited by 443
  2. 2017On Fairness and Calibrationcited by 406
  3. 2016Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatmentcited by 369
  4. 2018AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Biascited by 319
  5. 2020An Investigation of Why Overparameterization Exacerbates Spurious Correlationscited by 310
  6. 2018Empirical Risk Minimization under Fairness Constraintscited by 226
  7. 2017Avoiding Discrimination through Causal Reasoningcited by 194
  8. 2018Path-Specific Counterfactual Fairnesscited by 181
  9. 2019Feature relevance quantification in explainable AI: A causal problemcited by 167
  10. 2018Troubling Trends in Machine Learning Scholarshipcited by 108
  11. 2016A causal framework for discovering and removing direct and indirect discriminationcited by 71
  12. 2019PC-Fairness: A Unified Framework for Measuring Causality-based Fairnesscited by 67
  13. 2021Assessing the Fairness of AI Systems: AI Practitioners' Processes, Challenges, and Needs for Supportcited by 63
  14. 2017From Parity to Preference-based Notions of Fairness in Classificationcited by 60
  15. 2018Learning Optimal Fair Policiescited by 49
  16. 2018Human Perceptions of Fairness in Algorithmic Decision Making: A Case Study of Criminal Risk Predictioncited by 35
  17. 2020Large-scale empirical validation of Bayesian Network structure learning algorithms with noisy datacited by 29
  18. 2019General Fair Empirical Risk Minimizationcited by 23
  19. 2016On the (im)possibility of fairnesscited by 11
  20. 2019Disentangling Influence: Using Disentangled Representations to Audit Model Predictionscited by 11
  21. 2019Capuchin: Causal Database Repair for Algorithmic Fairnesscited by 6
  22. 2019Optimization Hierarchy for Fair Statistical Decision Problemscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 4; 2023: 8; 2024: 3; 2025: 7; 2026: 1.

23 papers.

Sort:

  1. 2022Bias Mitigation for Machine Learning Classifiers: A Comprehensive Surveycited by 125
  2. 2022Challenges in Applying Explainability Methods to Improve the Fairness of NLP Modelscited by 20
  3. 2023A Critical Survey on Fairness Benefits of Explainable AIcited by 16
  4. 2023Bias Propagation in Federated Learningcited by 12
  5. 2023Fix Fairness, Don't Ruin Accuracy: Performance Aware Fairness Repair using AutoMLcited by 9
  6. 2023Toward Operationalizing Pipeline-aware ML Fairness: A Research Agenda for Developing Practical Guidelines and Toolscited by 7
  7. 2022What Is Fairness? On the Role of Protected Attributes and Fictitious Worldscited by 6
  8. 2024A Large-Scale Empirical Study on Improving the Fairness of Image Classification Modelscited by 6
  9. 2022Explainable Global Fairness Verification of Tree-Based Classifierscited by 5
  10. 2023Beyond Demographic Parity: Redefining Equal Treatmentcited by 3
  11. 2025FairSense: Long-Term Fairness Analysis of ML-Enabled Systemscited by 3
  12. 2024Formalising Anti-Discrimination Law in Automated Decision Systemscited by 2
11 more
  1. 2025Explanations as Bias Detectors: A Critical Study of Local Post-hoc XAI Methods for Fairness Explorationcited by 2
  2. 2023Function Composition in Trustworthy Machine Learning: Implementation Choices, Insights, and Questionscited by 1
  3. 2023Feature Importance Disparities for Data Bias Investigationscited by 1
  4. 2024Mapping the Potential of Explainable AI for Fairness Along the AI Lifecyclecited by 1
  5. 2025Software Engineering Principles for Fairer Systems: Experiments with GroupCARTcited by 1
  6. 2025Argumentative Debates for Transparent Bias Detection [Technical Report]cited by 1
  7. 2023Towards AI Transparency and Accountability: A Global Framework for Exchanging Information on AI Systemscited by 0
  8. 2025A Critical Review of Predominant Bias in Neural Networkscited by 0
  9. 2025Whence Is A Model Fair? Fixing Fairness Bugs via Propensity Score Matchingcited by 0
  10. 2025Bridging Fairness and Explainability: Can Input-Based Explanations Promote Fairness in Hate Speech Detection?cited by 0
  11. 2026GESD: Beyond Outcome-Oriented Fairnesscited by 0