A Moral Framework for Understanding Fair ML through Economic Models of Equality of Opportunity

ABSTRACT

We map the recently proposed notions of algorithmic fairness to economic models of Equality of opportunity (EOP)---an extensively studied ideal of fairness in political philosophy. We formally show that through our conceptual mapping, many existing definition of algorithmic fairness, such as predictive value parity and equality of odds, can be interpreted as special cases of EOP. In this respect, our work serves as a unifying moral framework for understanding existing notions of algorithmic fairness. Most importantly, this framework allows us to explicitly spell out the moral assumptions underlying each notion of fairness, and interpret recent fairness impossibility results in a new light. Last but not least and inspired by luck egalitarian models of EOP, we propose a new family of measures for algorithmic fairness. We illustrate our proposal empirically and show that employing a measure of algorithmic (un)fairness when its underlying moral assumptions are not satisfied, can have devastating consequences for the disadvantaged group's welfare.

References

1. Richard J. Arneson. 1989. Equality and equal opportunity for welfare. Philosophical Studies: An International Journal for Philosophy in the Analytic Tradition 56, 1 (1989), 77--93.
2. Richard J. Arneson. 2015. Equality of Opportunity. In the Stanford Encyclopedia of Philosophy (summer 2015 ed.), Edward N. Zalta (Ed.). Metaphysics Research Lab, Stanford University.
3. Richard J. Arneson. 2018. Four Conceptions of equal opportunity. (2018).
4. Richard Berk, Hoda Heidari, Shahin Jabbari, Michael Kearns, and Aaron Roth. 2017. Fairness in Criminal Justice Risk Assessments: The State of the Art. arXiv preprint arXiv:1703.09207 (2017).
5. Joy Buolamwini and Timnit Gebru. 2018. Gender shades: Intersectional accuracy disparities in commercial gender classification. In Proceedings of the Conference on Fairness, Accountability and Transparency. 77--91.
6. Toon Calders, Asim Karim, Faisal Kamiran, Wasif Ali, and Xiangliang Zhang. 2013. Controlling attribute effect in linear regression. In Proceedings of the International Conference on Data Mining. IEEE, 71--80.
7. Gerald A. Cohen. 1989. On the currency of egalitarian justice. Ethics 99, 4 (1989), 906--944.
8. Cynthia Dwork, Moritz Hardt, Toniann Pitassi, Omer Reingold, and Richard Zemel. 2012. Fairness through awareness. In Proceedings of the Innovations in Theoretical Computer Science Conference. ACM, 214--226.
9. Ronald Dworkin. 1981. What is equality? Part 1: Equality of welfare. Philosophy & Public Affairs 10, 3 (1981), 185--246.
10. Ronald Dworkin. 1981. What is equality? Part 2: Equality of resources. Philosophy & Public Affairs 10, 4 (1981), 283--345.
11. Michael Feldman, Sorelle A. Friedler, John Moeller, Carlos Scheidegger, and Suresh Venkatasubramanian. 2015. Certifying and removing disparate impact. In Proceedings of the International Conference on Knowledge Discovery and Data Mining. ACM, 259--268.
12. Marc Fleurbaey. 2008. Fairness, responsibility, and welfare. Oxford University Press.
13. Sorelle A. Friedler, Carlos Scheidegger, and Suresh Venkatasubramanian. 2016. On the (im)possibility of fairness. arXiv preprint arXiv:1609.07236 (2016).
14. Moritz Hardt, Eric Price, and Nati Srebro. 2016. Equality of opportunity in supervised learning. In Proceedings of the 30th Conference on Neural Information Processing Systems. 3315--3323.
15. Hoda Heidari, Claudio Ferrari, Krishna P. Gummadi, and Andreas Krause. 2018. Fairness Behind a Veil of Ignorance: A Welfare Analysis for Automated Decision Making. In Proceedings of the 32nd Conference on Neural Information Processing Systems.
16. Faisal Kamiran and Toon Calders. 2009. Classifying without discriminating. In Proceedings of the 2nd International Conference on Computer, Control and Communication. IEEE, 1--6.
17. Toshihiro Kamishima, Shotaro Akaho, and Jun Sakuma. 2011. Fairness-aware learning through regularization approach. In Proceedings of the International Conference on Data Mining Workshops. IEEE, 643--650.
18. Jon Kleinberg, Sendhil Mullainathan, and Manish Raghavan. 2017. Inherent trade-offs in the fair determination of risk scores. In In proceedings of the 8th Innovations in Theoretical Computer Science Conference.
19. Arnaud Lefranc, Nicolas Pistolesi, and Alain Trannoy. 2009. Equality of opportunity and luck: Definitions and testable conditions, with an application to income in France. Journal of Public Economics 93, 11--12 (2009), 1189--1207.
20. M. Lichman. 2013. UCI Machine Learning Repository: Communities and Crime Data Set. http://archive.ics.uci.edu/ml/datasets/Communities+and+Crime.
21. John Rawls. 1958. Justice as fairness. The philosophical review 67, 2 (1958), 164--194.
22. John Rawls. 1971. A theory of justice. Harvard university press.
23. John E. Roemer. 1993. A pragmatic theory of responsibility for the egalitarian planner. Philosophy & Public Affairs (1993), 146--166.
24. John E. Roemer. 2002. Equality of opportunity: A progress report. Social Choice and Welfare 19, 2 (2002), 455--471.
25. John E. Roemer. 2009. Equality of opportunity. Harvard University Press.
26. John E. Roemer and Alain Trannoy. 2015. Equality of opportunity. In Handbook of income distribution. Vol. 2. Elsevier, 217--300.
27. Amartya Sen. 1979. Equality of What? The Tanner Lecture on Human Values (1979).
28. Till Speicher, Hoda Heidari, Nina Grgic-Hlaca, Krishna P. Gummadi, Adish Singla, Adrian Weller, and Muhammad Bilal Zafar. 2018. A Unified Approach to Quantifying Algorithmic Unfairness: Measuring Individual and Group Unfairness via Inequality Indices. In Proceedings of the International Conference on Knowledge Discovery and Data Mining.
29. Wikipedia. 2018. Equal opportunity. https://en.wikipedia.org/wiki/Equal_opportunity.
30. Muhammad Bilal Zafar, Isabel Valera, Manuel Gomez Rodriguez, and Krishna P Gummadi. 2017. Fairness beyond disparate treatment & disparate impact: Learning classification without disparate mistreatment. In Proceedings of the 26th International Conference on World Wide Web. 1171--1180.
31. Muhammad Bilal Zafar, Isabel Valera, Manuel Gomez Rodriguez, and Krishna P. Gummadi. 2017. Fairness Constraints: Mechanisms for Fair Classification. In Proceedings of the 20th International Conference on Artificial Intelligence and Statistics.

Index Terms

• Applied computing

  • Law, social and behavioral sciences

    • Economics

    • Sociology

• Computing methodologies

  • Machine learning

    • Learning paradigms

      • Supervised learning

    • Learning settings

      • Batch learning