skip to main content
10.1145/3366423.3380228acmconferencesArticle/Chapter ViewAbstractPublication PagesthewebconfConference Proceedingsconference-collections
research-article

Designing Fairly Fair Classifiers Via Economic Fairness Notions

Published: 20 April 2020 Publication History

Abstract

The past decade has witnessed a rapid growth of research on fairness in machine learning. In contrast, fairness has been formally studied for almost a century in microeconomics in the context of resource allocation, during which many general-purpose notions of fairness have been proposed. This paper explore the applicability of two such notions — envy-freeness and equitability — in machine learning. We propose novel relaxations of these fairness notions which apply to groups rather than individuals, and are compelling in a broad range of settings. Our approach provides a unifying framework by incorporating several recently proposed fairness definitions as special cases. We provide generalization bounds for our approach, and theoretically and experimentally evaluate the tradeoff between loss minimization and our fairness guarantees.

References

[1]
A. Agarwal, A. Beygelzimer, M. Dudik, J. Langford, and H. Wallach. 2018. A Reductions Approach to Fair Classification. In Proceedings of the 35th International Conference on Machine Learning (ICML). 60–69.
[2]
M. Aleksandrov and T. Walsh. 2018. Group envy freeness and group pareto efficiency in fair division with indivisible items. In In Proceedings of the 41st German Conference on Artificial Intelligence (KI). 57–72.
[3]
M. Altman, A. Wood, and E. Vayena. 2018. A harm-reduction framework for algorithmic fairness. IEEE Security & Privacy 16, 3 (2018), 34–45.
[4]
H. Aziz. 2019. Justifications of Welfare Guarantees under Normalized Utilities. arXiv preprint arXiv:1905.10774.
[5]
M. F. Balcan, F. Constantin, S. Iwata, and L. Wang. 2012. Learning valuation functions. In Proceedings of the 25th Conference on Computational Learning Theory (COLT). 4.1–4.24.
[6]
M. F. Balcan, T. Dick, R. Noothigattu, and A. D. Procaccia. 2019. Envy-Free Classification. In Proceedings of the 33rd Conference on Neural Information Processing Systems (NeurIPS). 1238–1248.
[7]
S. Barocas and A. D. Selbst. 2016. Big data’s disparate impact. Calif. L. Rev. 104(2016), 671.
[8]
J. Bartholdi, C. A. Tovey, and M. A. Trick. 1992. How hard Is It to Control an Election. Mathematical and Computer Modelling 16 (1992), 27–40.
[9]
O. Ben-Porat, F. Sandomirskiy, and M. Tennenholtz. 2019. Protecting the Protected Group: Circumventing Harmful Fairness. arXiv:1905.10546.
[10]
A. Blum, J. Jackson, T. Sandholm, and M. Zinkevich. 2004. Preference elicitation and query learning. Journal of Machine Learning Research 5, Jun (2004), 649–667.
[11]
C. Boutilier, K. Regan, and P. Viappiani. 2010. Simultaneous elicitation of preference features and utility. In Proceedings of the 24th AAAI Conference on Artificial Intelligence (AAAI). 1160–1167.
[12]
E. Budish. 2011. The combinatorial assignment problem: Approximate competitive equilibrium from equal incomes. Journal of Political Economy 119, 6 (2011), 1061–1103.
[13]
T. Calders, F. Kamiran, and M. Pechenizkiy. 2009. Building classifiers with independency constraints. In Proceedings of the IEEE International Conference on Data Mining Workshops. 13–18.
[14]
I. Caragiannis, D. Kurokawa, H. Moulin, A. D. Procaccia, N. Shah, and J. Wang. 2019. The unreasonable fairness of maximum Nash welfare. ACM Transactions on Economics and Computation (TEAC) 7, 3 (2019), 12.
[15]
U. Chajewska, D. Koller, and D. Ormoneit. 2001. Learning an agent’s utility function by observing behavior. In Proceedings of the 18th International Conference on Machine Learning (ICML). 35–42.
[16]
X. Chen, B. Fain, L. Lyu, and K. Munagala. 2019. Proportionally Fair Clustering. In Proceedings of the 36th International Conference on Machine Learning (ICML). 1032–1041.
[17]
A. Chouldechova. 2017. Fair prediction with disparate impact: A study of bias in recidivism prediction instruments. Big data 5, 2 (2017), 153–163.
[18]
V. Conitzer, R. Freeman, N. Shah, and J. W. Vaughan. 2019. Group fairness for the allocation of indivisible goods. In Proceedings of the 33rd AAAI Conference on Artificial Intelligence (AAAI). 1853–1860.
[19]
S. Diamond and S. Boyd. 2016. CVXPY: A Python-Embedded Modeling Language for Convex Optimization. Journal of Machine Learning Research 17, 83 (2016), 1–5.
[20]
C. Dwork, M. Hardt, T. Pitassi, O. Reingold, and R. Zemel. 2012. Fairness through awareness. In Proceedings of the 3rd Innovations in Theoretical Computer Science Conference (ITCS). 214–226.
[21]
B. Fain, A. Goel, and K. Munagala. 2016. The core of the participatory budgeting problem. In Proceedings of the 12th Conference on Web and Internet Economics (WINE). 384–399.
[22]
D. Foley. 1967. Resource allocation and the public sector. Yale Economics Essays 7(1967), 45–98.
[23]
D. Gale and L. S. Shapley. 1962. College Admissions and the Stability of Marriage. Americal Mathematical Monthly 69, 1 (1962), 9–15.
[24]
P. Gölz, A. Kahng, and A. D. Procaccia. 2019. Paradoxes in Fair Machine Learning. In Proceedings of the 32nd Conference on Neural Information Processing Systems (NeurIPS). 8340–8350.
[25]
M. Hardt, E. Price, and N. Srebro. 2016. Equality of opportunity in supervised learning. In Proceedings of the 30th Conference on Neural Information Processing Systems (NeurIPS). 3315–3323.
[26]
Ú. Hébert-Johnson, M. Kim, O. Reingold, and G. Rothblum. 2018. Multicalibration: Calibration for the (computationally-identifiable) masses. In Proceedings of the 35th International Conference on Machine Learning (ICML). 1944–1953.
[27]
H. Heidari, M. Loi, K. P. Gummadi, and A. Krause. 2019. A Moral Framework for Understanding Fair ML through Economic Models of Equality of Opportunity. In Proceedings of the Conference on Fairness, Accountability, and Transparency (FAT*). 181–190.
[28]
K. Holstein, J. W. Vaughan, H. Daumé III, M. Dudik, and H. Wallach. 2019. Improving fairness in machine learning systems: What do industry practitioners need?. In Proceedings of the Conference on Human Factors in Computing Systems (CHI). 600.
[29]
M. Kearns, S. Neel, A. Roth, and Z. S. Wu. 2018. Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness. In Proceedings of the 35th International Conference on Machine Learning (ICML). 2569–2577.
[30]
J. M. Kleinberg, S. Mullainathan, and M. Raghavan. 2017. Inherent Trade-Offs in the Fair Determination of Risk Scores. In Proceedings of the 8th Innovations in Theoretical Computer Science Conference (ITCS). 43:1–43:23.
[31]
M. J. Kusner, J. Loftus, C. Russell, and R. Silva. 2017. Counterfactual fairness. In Proceedings of the 31st Conference on Neural Information Processing Systems (NeurIPS). 4066–4076.
[32]
N. Lambert and Y. Shoham. 2009. Eliciting truthful answers to multiple-choice questions. In Proceedings of the 10th ACM Conference on Economics and Computation (EC). 109–118.
[33]
R. J. Lipton, E. Markakis, E. Mossel, and A. Saberi. 2004. On approximately fair allocations of indivisible goods. In Proceedings of the 6th ACM Conference on Economics and Computation (EC). 125–131.
[34]
L. T. Liu, S. Dean, E. Rolf, M. Simchowitz, and M. Hardt. 2018. Delayed impact of fair machine learning. arXiv:1803.04383.
[35]
A. K. Menon and R. C. Williamson. 2018. The cost of fairness in binary classification. In Proceedings of the Conference on Fairness, Accountability and Transparency (FAT). 107–118.
[36]
H. Moulin. 2004. Fair Division and Collective Welfare. MIT Press.
[37]
S. Mullainathan. 2018. Algorithmic Fairness and the Social Welfare Function. In Proceedings of the 19th ACM Conference on Economics and Computation (EC). 1–1.
[38]
A. Narayanan. 2018. Translation tutorial: 21 fairness definitions and their politics. In Proceedings of the Conference on Fairness, Accountability, and Transparency (FAT).
[39]
G. Ramnarayan. 2018. Equalizing Financial Impact in Supervised Learning. arXiv:1806.09211.
[40]
J. Rawls. 1971. A Theory of Justice. Harvard University Press.
[41]
S. Shalev-Shwartz and S. Ben-David. 2014. Understanding Machine Learning: From Theory to Algorithms. Cambridge University Press.
[42]
L. Shapley and H. Scarf. 1974. On cores and indivisibility. Journal of Mathematical Economics 1, 1 (1974), 23–37.
[43]
H. Steinhaus. 1948. The problem of fair division. Econometrica 16(1948), 101–104.
[44]
W. Stromquist. 1980. How to cut a cake fairly. Amer. Math. Monthly 87, 8 (1980), 640–644.
[45]
F. E. Su. 1999. Rental harmony: Sperner’s lemma in fair division. Amer. Math. Monthly 106, 10 (1999), 930–942.
[46]
B. Ustun, Y. Liu, and D. C. Parkes. 2019. Fairness without harm: Decoupled classifiers with preference guarantees. In Proceedings of the 36th International Conference on Machine Learning (ICML). 6373–6382.
[47]
H. Varian. 1974. Equity, envy and efficiency. Journal of Economic Theory 9 (1974), 63–91.
[48]
B. Woodworth, S. Gunasekar, M. I. Ohannessian, and N. Srebro. 2017. Learning Non-Discriminatory Predictors. In Proceedings of the 30th Conference on Computational Learning Theory (COLT). 1920–1953.
[49]
M. B. Zafar, I. Valera, M. Rodriguez, K. Gummadi, and A. Weller. 2017. From parity to preference-based notions of fairness in classification. In Proceedings of the 31st Conference on Neural Information Processing Systems (NeurIPS). 229–239.

Cited By

View all
  • (2023)Fair adaptive experimentsProceedings of the 37th International Conference on Neural Information Processing Systems10.5555/3666122.3666962(19157-19169)Online publication date: 10-Dec-2023
  • (2023)Pushing the limits of fairness in algorithmic decision-makingProceedings of the Thirty-Second International Joint Conference on Artificial Intelligence10.24963/ijcai.2023/806(7051-7056)Online publication date: 19-Aug-2023
  • (2022)Trade-offs between Group Fairness Metrics in Societal Resource AllocationProceedings of the 2022 ACM Conference on Fairness, Accountability, and Transparency10.1145/3531146.3533171(1095-1105)Online publication date: 21-Jun-2022
  • Show More Cited By

Index Terms

  1. Designing Fairly Fair Classifiers Via Economic Fairness Notions
        Index terms have been assigned to the content through auto-classification.

        Recommendations

        Comments

        Information & Contributors

        Information

        Published In

        cover image ACM Conferences
        WWW '20: Proceedings of The Web Conference 2020
        April 2020
        3143 pages
        ISBN:9781450370233
        DOI:10.1145/3366423
        Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

        Sponsors

        Publisher

        Association for Computing Machinery

        New York, NY, United States

        Publication History

        Published: 20 April 2020

        Permissions

        Request permissions for this article.

        Check for updates

        Author Tags

        1. Group envy-freeness
        2. fairness
        3. generalization
        4. group equitability

        Qualifiers

        • Research-article
        • Research
        • Refereed limited

        Conference

        WWW '20
        Sponsor:
        WWW '20: The Web Conference 2020
        April 20 - 24, 2020
        Taipei, Taiwan

        Acceptance Rates

        Overall Acceptance Rate 1,899 of 8,196 submissions, 23%

        Contributors

        Other Metrics

        Bibliometrics & Citations

        Bibliometrics

        Article Metrics

        • Downloads (Last 12 months)24
        • Downloads (Last 6 weeks)4
        Reflects downloads up to 01 Mar 2025

        Other Metrics

        Citations

        Cited By

        View all
        • (2023)Fair adaptive experimentsProceedings of the 37th International Conference on Neural Information Processing Systems10.5555/3666122.3666962(19157-19169)Online publication date: 10-Dec-2023
        • (2023)Pushing the limits of fairness in algorithmic decision-makingProceedings of the Thirty-Second International Joint Conference on Artificial Intelligence10.24963/ijcai.2023/806(7051-7056)Online publication date: 19-Aug-2023
        • (2022)Trade-offs between Group Fairness Metrics in Societal Resource AllocationProceedings of the 2022 ACM Conference on Fairness, Accountability, and Transparency10.1145/3531146.3533171(1095-1105)Online publication date: 21-Jun-2022
        • (2022)Multi-disciplinary fairness considerations in machine learning for clinical trialsProceedings of the 2022 ACM Conference on Fairness, Accountability, and Transparency10.1145/3531146.3533154(906-924)Online publication date: 21-Jun-2022
        • (2022)Achievement and Fragility of Long-term EquitabilityProceedings of the 2022 AAAI/ACM Conference on AI, Ethics, and Society10.1145/3514094.3534132(675-685)Online publication date: 26-Jul-2022
        • (2022)Socially-Equitable Interactive Graph Information Fusion-based Prediction for Urban Dockless E-Scooter SharingProceedings of the ACM Web Conference 202210.1145/3485447.3512145(3269-3279)Online publication date: 25-Apr-2022
        • (2022)Learning Optimal Fair Scoring Systems for Multi-Class Classification2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI)10.1109/ICTAI56018.2022.00036(197-204)Online publication date: Oct-2022
        • (2021)Two-sided fairness in rankings via Lorenz dominanceProceedings of the 35th International Conference on Neural Information Processing Systems10.5555/3540261.3540919(8596-8608)Online publication date: 6-Dec-2021
        • (2021)Ensuring Fairness under Prior Probability ShiftsProceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society10.1145/3461702.3462596(414-424)Online publication date: 21-Jul-2021
        • (2021)Rawlsian Fair Adaptation of Deep Learning ClassifiersProceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society10.1145/3461702.3462592(936-945)Online publication date: 21-Jul-2021
        • Show More Cited By

        View Options

        Login options

        View options

        PDF

        View or Download as a PDF file.

        PDF

        eReader

        View online with eReader.

        eReader

        HTML Format

        View this article in HTML Format.

        HTML Format

        Figures

        Tables

        Media

        Share

        Share

        Share this Publication link

        Share on social media