mlsanityData to 14 Oct 2026

Beyond Demographic Parity: Redefining Equal Treatment

arXiv 2303.08040 ↗First posted 14 Mar 2023cs.LG cs.CYcited by 3

Not on the map. Why?

Abstract (arXiv)

Liberalism-oriented political philosophy reasons that all individuals should be treated equally independently of their protected characteristics. Related work in machine learning has translated the concept of equal treatment into terms of equal outcome and measured it as demographic parity (also called statistical parity). Our analysis reveals that the two concepts of equal outcome and equal treatment diverge; therefore, demographic parity does not faithfully represent the notion of equal treatment. We propose a new formalization for equal treatment by (i) considering the influence of feature values on predictions, such as computed by Shapley values decomposing predictions across its features, (ii) defining distributions of explanations, and (iii) comparing explanation distributions between populations with different protected characteristics. We show the theoretical properties of our notion of equal treatment and devise a classifier two-sample test based on the AUC of an equal treatment inspector. We study our formalization of equal treatment on synthetic and natural data. We release textttexplanationspace, an open-source Python package with methods and tutorials.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 45 of its 97 references that are in the map. First posted on arXiv 14 Mar 2023.

Builds on

45 of 97 references.

References · 45

  1. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  2. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,166
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  4. 2016Equality of Opportunity in Supervised Learningcited by 2,007
  5. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,917
  6. 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,552
  7. 2018Sanity Checks for Saliency Mapscited by 1,156
  8. 2018A Survey Of Methods For Explaining Black Box Modelscited by 973
  9. 2017Counterfactual Fairnesscited by 804
  10. 2016Fair prediction with disparate impact: A study of bias in recidivism prediction instrumentscited by 672
  11. 2019Data Shapley: Equitable Valuation of Data for Machine Learningcited by 629
  12. 2016Inherent Trade-Offs in the Fair Determination of Risk Scorescited by 586
33 more
  1. 2018Towards Robust Interpretability with Self-Explaining Neural Networkscited by 505
  2. 2021Deep Neural Networks and Tabular Data: A Surveycited by 491
  3. 2021Retiring Adult: New Datasets for Fair Machine Learningcited by 449
  4. 2019Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methodscited by 443
  5. 2017Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraintscited by 420
  6. 2017Algorithmic decision making and the cost of fairnesscited by 403
  7. 2017Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairnesscited by 384
  8. 2020Closing the AI Accountability Gap: Defining an End-to-End Framework for Internal Algorithmic Auditingcited by 384
  9. 2019The many Shapley values for model explanationcited by 344
  10. 2016Revisiting Classifier Two-Sample Testscited by 268
  11. 2016Model-Agnostic Interpretability of Machine Learningcited by 219
  12. 2019Explaining individual predictions when features are dependent: More accurate approximations to Shapley valuescited by 208
  13. 2015Censoring Representations with an Adversarycited by 192
  14. 2019Towards Fairer Datasets: Filtering and Balancing the Distribution of the People Subtree in the ImageNet Hierarchycited by 156
  15. 2022Leveraging Unlabeled Data to Predict Out-of-Distribution Performancecited by 145
  16. 2018Explaining Explanations in AIcited by 137
  17. 2020Learning Deep Kernels for Non-Parametric Two-Sample Testscited by 130
  18. 2020True to the Model or True to the Data?cited by 126
  19. 2019Asymmetric Shapley values: incorporating causal knowledge into model-agnostic explainabilitycited by 114
  20. 2018L-Shapley and C-Shapley: Efficient Model Interpretation for Structured Datacited by 100
  21. 2022The Shapley Value in Machine Learningcited by 98
  22. 2021A Survey on Bias in Visual Datasetscited by 84
  23. 2018A Moral Framework for Understanding of Fair ML through Economic Models of Equality of Opportunitycited by 53
  24. 2021Do We Really Need Deep Learning Models for Time Series Forecasting?cited by 45
  25. 2020Efficient computation and analysis of distributional Shapley valuescited by 38
  26. 2018POTs: Protective Optimization Technologiescited by 28
  27. 2019Explaining black box decisions by Shapley cohort refinementcited by 26
  28. 2021Measuring Model Biases in the Absence of Ground Truthcited by 24
  29. 2022Marrying Fairness and Explainability in Supervised Learningcited by 23
  30. 2021RATT: Leveraging Unlabeled Data to Guarantee Generalizationcited by 20
  31. 2021Towards the Right Kind of Fairness in AIcited by 15
  32. 2022Monitoring Model Deterioration with Explainable Uncertainty Estimation via Non-parametric Bootstrapcited by 9
  33. 2022Explanation Shift: Detecting distribution shifts on tabular data via the explanation spacecited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 1; 2025: 0; 2026: 1.

3 papers.

  1. 2023Bias Testing and Mitigation in LLM-based Code Generationcited by 53
  2. 2024Fairness Auditing with Multi-Agent Collaborationcited by 2
  3. 2026Statistical and Structural Approaches to Algorithmic Fairnesscited by 0