Papers
Topics
Authors
Recent
Search
2000 character limit reached

Procedural Fairness Through Decoupling Objectionable Data Generating Components

Published 5 Nov 2023 in cs.CY, cs.AI, and cs.LG | (2311.14688v3)

Abstract: We reveal and address the frequently overlooked yet important issue of disguised procedural unfairness, namely, the potentially inadvertent alterations on the behavior of neutral (i.e., not problematic) aspects of data generating process, and/or the lack of procedural assurance of the greatest benefit of the least advantaged individuals. Inspired by John Rawls's advocacy for pure procedural justice, we view automated decision-making as a microcosm of social institutions, and consider how the data generating process itself can satisfy the requirements of procedural fairness. We propose a framework that decouples the objectionable data generating components from the neutral ones by utilizing reference points and the associated value instantiation rule. Our findings highlight the necessity of preventing disguised procedural unfairness, drawing attention not only to the objectionable data generating components that we aim to mitigate, but also more importantly, to the neutral components that we intend to keep unaffected.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (100)
  1. Elizabeth Anderson. What is the point of equality? Ethics, 109(2):287–337, 1999.
  2. Fairness and Machine Learning: Limitations and Opportunities. fairmlbook.org, 2019. http://www.fairmlbook.org.
  3. English with an accent: Language, ideology, and discrimination in the United States. Taylor & Francis, 2022.
  4. Brian Barry. Political Argument (Routledge Revivals). Routledge, 2010.
  5. John Baugh. Linguistic profiling. In Black Linguistics, pp.  167–180. Routledge, 2005.
  6. Adult. UCI Machine Learning Repository, 1996.
  7. Understanding constraints and residential satisfaction among low-income single-parent families. Environment and Behavior, 29(4):532–553, 1997.
  8. US Census Bureau. 2021 ACS 1-Year PUMS Data Dictionary. American Community Survey (ACS), 2021.
  9. Building classifiers with independency constraints. In 2009 IEEE International Conference on Data Mining Workshops, pp.  13–18. IEEE, 2009.
  10. Fairness transferability subject to bounded distribution shift. In Advances in Neural Information Processing Systems, 2022.
  11. Model transferability with responsive decision subjects. In International Conference on Machine Learning, pp.  4921–4952. PMLR, 2023.
  12. Silvia Chiappa. Path-specific counterfactual fairness. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 33, pp.  7801–7808, 2019.
  13. Alexandra Chouldechova. Fair prediction with disparate impact: A study of bias in recidivism prediction instruments. Big Data, 5(2):153–163, 2017.
  14. Gerald A Cohen. On the currency of egalitarian justice. Ethics, 99(4):906–944, 1989.
  15. Fair transfer learning with missing protected attributes. In Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society, pp.  91–98, 2019.
  16. Counterfactual risk assessments, evaluation, and fairness. In Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency, pp.  582–593, 2020.
  17. Causal modeling for fairness in dynamical systems. In International Conference on Machine Learning, pp.  2185–2195. PMLR, 2020.
  18. Kimberle Crenshaw. Mapping the margins: Intersectionality, identity politics, and violence against women of color. Stan. L. Rev., 43, 1990.
  19. Minimax group fairness: Algorithms and experiments. In Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society, pp.  66–76, 2021.
  20. Compas risk scales: Demonstrating accuracy equity and predictive parity. Northpointe Inc, 2016.
  21. Retiring adult: New datasets for fair machine learning. In Advances in Neural Information Processing Systems, volume 34, pp.  6478–6490, 2021.
  22. Fairness through awareness. In Proceedings of the 3rd Innovations in Theoretical Computer Science Conference, pp.  214–226, 2012.
  23. Exogeneity. Econometrica: Journal of the Econometric Society, pp.  277–304, 1983.
  24. Group-fair classification with strategic agents. In Proceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency, pp.  389–399, 2023.
  25. An intersectional definition of fairness. In 2020 IEEE 36th International Conference on Data Engineering (ICDE), pp.  1918–1921. IEEE, 2020.
  26. Equalizing recourse across groups. arXiv preprint arXiv:1909.03166, 2019.
  27. Strategic classification. In Proceedings of the 2016 ACM Conference on Innovations in Theoretical Computer Science, pp.  111–122, 2016a.
  28. Equality of opportunity in supervised learning. In Advances in Neural Information Processing Systems, pp.  3315–3323, 2016b.
  29. Fairness behind a veil of ignorance: A welfare analysis for automated decision making. In Advances in Neural Information Processing Systems, volume 31, 2018.
  30. A moral framework for understanding fair ml through economic models of equality of opportunity. In Proceedings of the Conference on Fairness, Accountability, and Transparency, pp.  181–190, 2019a.
  31. On the long-term impact of algorithmic decision policies: Effort unfairness and feature segregation through social learning. In International Conference on Machine Learning, pp.  2692–2701. PMLR, 2019b.
  32. Nonlinear causal discovery with additive noise models. In Advances in Neural Information Processing Systems, volume 21, 2008.
  33. The disparate effects of strategic manipulation. In Proceedings of the 2019 Conference on Fairness, Accountability, and Transparency, pp.  259–268, 2019.
  34. Principal fairness for human and algorithmic decision-making. arXiv preprint arXiv:2005.10400, 2020.
  35. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In International Conference on Machine Learning, pp.  448–456. PMLR, 2015.
  36. Courtney G Joslin. Marital status discrimination 2.0. Boston University Law Review, 95(3):805, 2015.
  37. The effect of physical height on workplace success and income: Preliminary test of a theoretical model. Journal of Applied Psychology, 89(3):428, 2004.
  38. Quantifying explainable discrimination and removing illegal discrimination in automated decision making. Knowledge and Information Systems, 35(3):613–644, 2013.
  39. The Ethical Algorithm: The Science of Socially Aware Algorithm Design. Oxford University Press, 2019.
  40. Preventing fairness gerrymandering: Auditing and learning for subgroup fairness. In International Conference on Machine Learning, pp.  2564–2572. PMLR, 2018.
  41. Avoiding discrimination through causal reasoning. In Advances in Neural Information Processing Systems, volume 30, pp.  656–666, 2017.
  42. Auto-encoding variational bayes. In International Conference on Learning Representations, 2014.
  43. Optimization by simulated annealing. Science, 220(4598):671–680, 1983.
  44. Self-normalizing neural networks. In Advances in Neural Information Processing Systems, volume 30, pp.  971–980, 2017.
  45. Inherent trade-offs in the fair determination of risk scores. In Proceedings of the 8th Innovations in Theoretical Computer Science Conference, 2017.
  46. Youjin Kong. Are ”intersectionally fair” ai algorithms really fair to women of color? a philosophical analysis. In Proceedings of the 2022 ACM Conference on Fairness, Accountability, and Transparency, pp.  485–494, 2022.
  47. Counterfactual fairness. In Advances in Neural Information Processing Systems, pp.  4066–4076, 2017.
  48. Steffen L Lauritzen. Graphical Models, volume 17. Clarendon Press, 1996.
  49. No room for new families? a field experiment measuring rental discrimination against same-sex couples and single parents. Social Problems, 58(3):389–409, 2011.
  50. On the fairness of disentangled representations. In Advances in Neural Information Processing Systems, volume 32, 2019.
  51. Causal reasoning for algorithmic fairness. arXiv preprint arXiv:1805.05859, 2018.
  52. The variational fair autoencoder. In International Conference on Learning Representations, 2016.
  53. Games and Decisions: Introduction and Critical Survey. Courier Corporation, 1989.
  54. Learning adversarially fair and transferable representations. arXiv preprint arXiv:1802.06309, 2018.
  55. Survey on causal-based machine learning fairness notions. arXiv preprint arXiv:2010.09553, 2020.
  56. Minimax pareto fairness: A multi objective perspective. In International Conference on Machine Learning, pp.  6755–6764. PMLR, 2020.
  57. A survey on bias and fairness in machine learning. ACM Computing Surveys, 54(6):1–35, 2021.
  58. The social cost of strategic classification. In Proceedings of the 2019 Conference on Fairness, Accountability, and Transparency, pp.  230–239, 2019.
  59. Fairness in risk assessment instruments: Post-processing to achieve counterfactual equalized odds. In Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency, pp.  386–400, 2021.
  60. Fair inference on outcomes. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 32, pp.  1931–1940, 2018.
  61. Learning optimal fair policies. In International Conference on Machine Learning, pp.  4674–4682. PMLR, 2019.
  62. Optimal training of fair predictive models. In Conference on Causal Learning and Reasoning, pp.  594–617. PMLR, 2022.
  63. Causal conceptions of fairness and their consequences. In International Conference on Machine Learning, pp.  16848–16887. PMLR, 2022.
  64. Cathy O’neil. Weapons of Math Destruction: How Big Data Increases Inequality and Threatens Democracy. Crown, 2017.
  65. Judea Pearl. Direct and indirect effects. In Proceedings of the Seventeenth Conference on Uncertainty and Artificial Intelligence, pp.  411–420, 2001.
  66. Judea Pearl. Causality. Cambridge University Press, 2009.
  67. Performative prediction. In International Conference on Machine Learning, pp.  7599–7609. PMLR, 2020.
  68. The effect of adolescent experience on labor market outcomes: The case of height. Journal of Political Economy, 112(5):1019–1053, 2004.
  69. Elements of Causal Inference: Foundations and Learning Algorithms. The MIT Press, 2017.
  70. Obesity stigma: Important considerations for public health. American Journal of Public Health, 100(6):1019–1028, 2010.
  71. John Rawls. A Theory of Justice. Harvard University Press, 1971.
  72. John Rawls. Justice as Fairness: A Restatement. Harvard University Press, 2001.
  73. Robust fairness under covariate shift. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pp.  9419–9427, 2021.
  74. Thomas Richardson. Markov properties for acyclic directed mixed graphs. Scandinavian Journal of Statistics, 30:145–157, 2003.
  75. Identifiability and exchangeability for direct and indirect effects. Epidemiology, 3:143–155, 1992.
  76. Donald B Rubin. Estimating causal effects of treatments in randomized and nonrandomized studies. Journal of Educational Psychology, 66(5):688, 1974.
  77. Donald B Rubin. Causal inference using potential outcomes: Design, modeling, decisions. Journal of the American Statistical Association, 100(469):322–331, 2005.
  78. Interventional fairness: Causal database repair for algorithmic fairness. In Proceedings of the 2019 International Conference on Management of Data, pp.  793–810, 2019.
  79. How do fairness definitions fare? examining public attitudes towards algorithmic definitions of fairness. In Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society, pp.  99–106, 2019.
  80. Causal inference with a graphical hierarchy of interventions. The Annals of Statistics, pp.  2433–2466, 2016.
  81. Fair representation learning through implicit path alignment. In International Conference on Machine Learning, pp.  20156–20175. PMLR, 2022.
  82. Fairness violations and mitigation under covariate shift. In Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency, pp.  3–13, 2021.
  83. Learning controllable fair representations. In The 22nd International Conference on Artificial Intelligence and Statistics, pp.  2164–2173, 2019.
  84. Peter Spirtes. Directed cyclic graphical representations of feedback models. In Proceedings of the Eleventh Conference on Uncertainty in Artificial Intelligence, pp.  491–498, 1995.
  85. Causation, Prediction, and Search. Springer New York, 1993.
  86. Tier balancing: Towards dynamic fairness over underlying causal factors. In International Conference on Learning Representations, 2023a.
  87. What-is and how-to for fairness in machine learning: A survey, reflection, and perspective. ACM Computing Surveys, 55(13s):1–37, 2023b.
  88. Actionable recourse in linear classification. In Proceedings of the Conference on Fairness, Accountability, and Transparency, pp.  10–19, 2019.
  89. Odds ratios for mediation analysis for a dichotomous outcome. American Journal of Epidemiology, 172(12):1339–1348, 2010.
  90. On the fairness of causal algorithmic recourse. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, pp.  9584–9594, 2022.
  91. Pc-fairness: A unified framework for measuring causality-based fairness. In Advances in Neural Information Processing Systems, volume 32, pp.  3399–3409, 2019.
  92. Fairness beyond disparate treatment & disparate impact: Learning classification without disparate mistreatment. In Proceedings of the 26th International Conference on World Wide Web, pp.  1171–1180, 2017.
  93. Learning fair representations. In International Conference on Machine Learning, pp.  325–333. PMLR, 2013.
  94. Equality of opportunity in classification: A causal approach. In Advances in neural information processing systems, volume 31, 2018a.
  95. Fairness in decision-making – the causal explanation formula. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 32, 2018b.
  96. On the identifiability of the post-nonlinear causal model. In 25th Conference on Uncertainty in Artificial Intelligence, pp.  647–655. AUAI Press, 2009.
  97. A causal framework for discovering and removing direct and indirect discrimination. In Proceedings of the 26th International Joint Conference on Artificial Intelligence, pp.  3929–3935, 2017.
  98. Fairness in learning-based sequential decision algorithms: A survey. In Handbook of Reinforcement Learning and Control, pp.  525–555. Springer, 2021.
  99. Inherent tradeoffs in learning fair representations. The Journal of Machine Learning Research, 23(1):2527–2552, 2022.
  100. Conditional learning of fair representations. In International Conference on Learning Representations, 2020.
Citations (1)
View on Semantic Scholar

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now

Collections

Sign up for free to add this paper to one or more collections.

Sign Up

Tweets

Sign up for free to view the 1 tweet with 0 likes about this paper.

Sign Up for Free