Fairness: A Formal-Methods Perspective
Sensitive decisions of large-scale societal impact are increasingly being delegated to opaque software—a trend that is unlikely to slow down in the near future. The issue of fairness and bias of decision-making algorithms has thus become a multifaceted, interdisciplinary concern, attracting the attention of computer scientists, law scholars, policy makers, journalists, and many others. In this expository paper, I will outline some of the research questions we have been studying about fairness through the lens of formal methods.
The work described in this talk is in collaboration with a fantastic group of students and researchers: Samuel Drews, Aditya Nori, Loris D’Antoni, Justin Hsu, Calvin Smith, and David Merrell. The work described is generously supported by the National Science Foundation (NSF) grant #1704117.
- 1.Albarghouthi, A., D’Antoni, L., Drews, S., Nori, A.V.: Fairsquare: probabilistic verification of program fairness. In: Proceedings of the ACM on Programming Languages (OOPSLA), vol. 1, pp. 80:1–80:30, October 2017. http://doi.acm.org/10.1145/3133904
- 3.Albarghouthi, A., Hsu, J.: Synthesizing coupling proofs of differential privacy. In: Proceedings of the ACM on Programming Languages (POPL), vol. 2, pp. 58:1–58:30 (2018). http://doi.acm.org/10.1145/3158146
- 4.Dwork, C., Hardt, M., Pitassi, T., Reingold, O., Zemel, R.S.: Fairness through awareness. In: Innovations in Theoretical Computer Science 2012, Cambridge, MA, USA, 8–10 January 2012, pp. 214–226 (2012)Google Scholar
- 6.Feldman, M., Friedler, S.A., Moeller, J., Scheidegger, C., Venkatasubramanian, S.: Certifying and removing disparate impact. In: Proceedings of the 21st ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Sydney, NSW, Australia, 10–13 August 2015, pp. 259–268 (2015). http://doi.acm.org/10.1145/2783258.2783311
- 7.Hardt, M., Price, E., Srebro, N.: Equality of opportunity in supervised learning. CoRR abs/1610.02413 (2016). http://arxiv.org/abs/1610.02413
- 8.Kearns, M., Roth, A., Wu, Z.S.: Meritocratic fairness for cross-population selection. In: International Conference on Machine Learning, pp. 1828–1836 (2017)Google Scholar
- 9.Kleinberg, J., Mullainathan, S., Raghavan, M.: Inherent trade-offs in the fair determination of risk scores. In: ITCS (2017)Google Scholar
- 10.Lyu, M., Su, D., Li, N.: Understanding the Sparse Vector Technique for differential privacy. In: Appeared at the International Conference on Very Large Data Bases (VLDB), Munich, Germany, vol. 10, pp. 637–648 (2017). http://arxiv.org/abs/1603.01699
- 11.Merrell, D., Albarghouthi, A., DAntoni, L.: Weighted model integration with orthogonal transformations. In: Proceedings of the 26th International Joint Conference on Artificial Intelligence, pp. 4610–4616. AAAI Press (2017)Google Scholar
- 12.Pedreshi, D., Ruggieri, S., Turini, F.: Discrimination-aware data mining. In: Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 560–568. ACM (2008)Google Scholar
- 13.Zemel, R.S., Wu, Y., Swersky, K., Pitassi, T., Dwork, C.: Learning fair representations. In: Proceedings of the 30th International Conference on Machine Learning, ICML 2013, Atlanta, GA, USA, 16–21 June 2013, pp. 325–333 (2013). http://jmlr.org/proceedings/papers/v28/zemel13.html