Document Open Access Logo

An Algorithmic Framework for Fairness Elicitation

Authors Christopher Jung, Michael Kearns, Seth Neel, Aaron Roth, Logan Stapleton, Zhiwei Steven Wu

PDF
Thumbnail PDF

File

LIPIcs.FORC.2021.2.pdf
  • Filesize: 1.45 MB
  • 19 pages

Document Identifiers

Author Details

Christopher Jung
  • University of Pennsylvania, Philadelphia, PA, USA
Michael Kearns
  • University of Pennsylvania, Philadelphia, PA, USA
Seth Neel
  • Harvard University, Cambridge, MA, USA
Aaron Roth
  • University of Pennsylvania, Philadelphia, PA, USA
Logan Stapleton
  • University of Minnesota, Minneapolis, MN, USA
Zhiwei Steven Wu
  • Carnegie Mellon University, Pittsburgh, PA, USA

Cite AsGet BibTex

Christopher Jung, Michael Kearns, Seth Neel, Aaron Roth, Logan Stapleton, and Zhiwei Steven Wu. An Algorithmic Framework for Fairness Elicitation. In 2nd Symposium on Foundations of Responsible Computing (FORC 2021). Leibniz International Proceedings in Informatics (LIPIcs), Volume 192, pp. 2:1-2:19, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2021)
https://doi.org/10.4230/LIPIcs.FORC.2021.2

Abstract

We consider settings in which the right notion of fairness is not captured by simple mathematical definitions (such as equality of error rates across groups), but might be more complex and nuanced and thus require elicitation from individual or collective stakeholders. We introduce a framework in which pairs of individuals can be identified as requiring (approximately) equal treatment under a learned model, or requiring ordered treatment such as "applicant Alice should be at least as likely to receive a loan as applicant Bob". We provide a provably convergent and oracle efficient algorithm for learning the most accurate model subject to the elicited fairness constraints, and prove generalization bounds for both accuracy and fairness. This algorithm can also combine the elicited constraints with traditional statistical fairness notions, thus "correcting" or modifying the latter by the former. We report preliminary findings of a behavioral study of our framework using human-subject fairness constraints elicited on the COMPAS criminal recidivism dataset.

Subject Classification

ACM Subject Classification
  • Theory of computation → Machine learning theory
Keywords
  • Fairness
  • Fairness Elicitation

Metrics

  • Access Statistics
  • Total Accesses (updated on a weekly basis)
    0
    PDF Downloads
    0
    Metadata Views

Related Versions

References

  1. Matthew Adler. Aggregating moral preferences. Economics and Philosophy, 32:283-321, 2016. Google Scholar
  2. Alekh Agarwal, Alina Beygelzimer, Miroslav Dudik, John Langford, and Hanna Wallach. A reductions approach to fair classification. In International Conference on Machine Learning, pages 60-69, 2018. Google Scholar
  3. Alekh Agarwal, Alina Beygelzimer, Miroslav Dudík, John Langford, and Hanna M. Wallach. A reductions approach to fair classification. In Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsmässan, Stockholm, Sweden, July 10-15, 2018, pages 60-69, 2018. URL: http://proceedings.mlr.press/v80/agarwal18a.html.
  4. Alekh Agarwal, Miroslav Dudík, and Zhiwei Steven Wu. Fair regression: Quantitative definitions and reduction-based algorithms. In Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9-15 June 2019, Long Beach, California, USA, pages 120-129, 2019. URL: http://proceedings.mlr.press/v97/agarwal19d.html.
  5. Edmond Awad, Sohan Dsouza, Richard Kim, Jonathan Schulz, Joseph Henrich, Azim Shariff, Jean-François Bonnefon, and Iyad Rahwan. The moral machine experiment. Nature, 563:59–64, 2018. Google Scholar
  6. Han Bao, Gang Niu, and Masashi Sugiyama. Classification from pairwise similarity and unlabeled data. In ICML, 2018. Google Scholar
  7. Sugato Basu, Arindam Banerjee, and Raymond J. Mooney. Active semi-supervision for pairwise constrained clustering. In Proceedings of the SIAM International Conference on Data Mining, (SDM-2004), pp. , Lake Buena Vista, FL, pages 333 - -344, 2004. Google Scholar
  8. Yahav Bechavod, Christopher Jung, and Steven Z. Wu. Metric-free individual fairness in online learning. In Hugo Larochelle, Marc'Aurelio Ranzato, Raia Hadsell, Maria-Florina Balcan, and Hsuan-Tien Lin, editors, Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual, 2020. URL: https://proceedings.neurips.cc/paper/2020/hash/80b618ebcac7aa97a6dac2ba65cb7e36-Abstract.html.
  9. Reuben Binns, Max Van Kleek, Michael Veale, Ulrik Lyngs, Jun Zhao, and Nigel Shadbolt. "It’s reducing a human being to a percentage": Perceptions of justice in algorithmic decisions. In Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems, page 377. ACM, 2018. Google Scholar
  10. Lawrence Blum. Moral Perception and Particularity. Cambridge University Press, 1994. Google Scholar
  11. Anna Brown, Alexandra Chouldechova, Emily Putnam-Hornstein, Andrew Tobin, and Rhema Vaithianathan. Toward algorithmic accountability in public services: A qualitative study of affected community perspectives on algorithmic decision-making in child welfare services. In Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems, CHI 2019, Glasgow, Scotland, UK, May 04-09, 2019, page 41, 2019. URL: https://doi.org/10.1145/3290605.3300271.
  12. Hao-Fei Cheng, Logan Stapleton, Ruiqi Wang, Paige Bullock, Alexandra Chouldechova, Zhiwei Steven Wu, and Haiyi Zhu. Soliciting stakeholders' fairness notions in child maltreatment predictive systems. In Proceedings of the ACM Conference on Human Factors in Computing Systems (CHI), 2021. URL: http://arxiv.org/abs/2102.01196.
  13. Vincent Conitzer, Walter Sinnott-Armstrong, Jana Schaich Borg, Yuan Deng, and Max Kramer. Moral decision making frameworks for artificial intelligence. In Proceedings of the International Symposium on Artificial Intelligence and Mathematics (ISAIM), 2018. Google Scholar
  14. Sam Corbett-Davies and Sharad Goel. The measure and mismeasure of fairness: A critical review of fair machine learning. CoRR, abs/1808.00023, 2018. URL: http://arxiv.org/abs/1808.00023.
  15. Jonathan Dodge, Q. Vera Liao, Yunfeng Zhang, Rachel K. E. Bellamy, and Casey Dugan. Explaining models: An empirical study of how explanations impact fairness judgment. In Proceedings of the 24th International Conference on Intelligent User Interfaces, IUI '19, pages 275-285, New York, NY, USA, 2019. ACM. URL: https://doi.org/10.1145/3301275.3302310.
  16. Carmel Domshlak, Eyke Hüllermeier, Souhila Kaci, and Henri Prade. Preferences in ai: An overview. Artificial Intelligence, 175(7):1037 - -1052, 2011. URL: https://doi.org/10.1016/j.artint.2011.03.004.
  17. Cynthia Dwork, Moritz Hardt, Toniann Pitassi, Omer Reingold, and Richard Zemel. Fairness through awareness. In Proceedings of the 3rd innovations in theoretical computer science conference, pages 214-226. ACM, 2012. Google Scholar
  18. Cynthia Dwork, Moritz Hardt, Toniann Pitassi, Omer Reingold, and Richard S. Zemel. Fairness through awareness. In Innovations in Theoretical Computer Science 2012, Cambridge, MA, USA, January 8-10, 2012, pages 214-226, 2012. URL: https://doi.org/10.1145/2090236.2090255.
  19. Vitaly Feldman, Parikshit Gopalan, Subhash Khot, and Ashok Kumar Ponnuswami. On agnostic learning of parities, monomials, and halfspaces. SIAM Journal on Computing, 39(2):606-645, 2009. Google Scholar
  20. Vitaly Feldman, Venkatesan Guruswami, Prasad Raghavendra, and Yi Wu. Agnostic learning of monomials by halfspaces is hard. SIAM Journal on Computing, 41(6):1558-1590, 2012. Google Scholar
  21. Rachel Freedman, Jana Schaich Borg, Walter Sinnott-Armstrong, John P. Dickerson, and Vincent Conitzer. Adapting a kidney exchange algorithm to align with human values. Artificial Intelligence, 283:103261, 2020. Google Scholar
  22. Yoav Freund and Robert E Schapire. Game theory, on-line prediction and boosting. In COLT, volume 96, pages 325-332. Citeseer, 1996. Google Scholar
  23. Stephen Gillen, Christopher Jung, Michael Kearns, and Aaron Roth. Online learning with an unknown fairness metric. In Advances in Neural Information Processing Systems, pages 2600-2609, 2018. Google Scholar
  24. Nina Grgic-Hlaca, Elissa M. Redmiles, Krishna P. Gummadi, and Adrian Weller. Human perceptions of fairness in algorithmic decision making: A case study of criminal risk prediction. In Proceedings of the 2018 World Wide Web Conference, WWW '18, pages 903-912. International World Wide Web Conferences Steering Committee, 2018. URL: https://doi.org/10.1145/3178876.3186138.
  25. Nina Grgić-Hlača, Muhammad Bilal Zafar, Krishna P. Gummadi, and Adrian Weller. Beyond distributive fairness in algorithmic decision making: Feature selection for procedurally fair learning. In Proceedings of the 32nd AAAI Conference on Artificial Intelligence, 2018. Google Scholar
  26. Moritz Hardt, Eric Price, and Nati Srebro. Equality of opportunity in supervised learning. In Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, December 5-10, 2016, Barcelona, Spain, pages 3315-3323, 2016. URL: http://papers.nips.cc/paper/6374-equality-of-opportunity-in-supervised-learning.
  27. Kenneth Holstein, Jennifer Wortman Vaughan, Hal Daumé III, Miroslav Dudík, and Hanna M. Wallach. Improving fairness in machine learning systems: What do industry practitioners need? In Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems, CHI 2019, Glasgow, Scotland, UK, May 04-09, 2019, page 600, 2019. URL: https://doi.org/10.1145/3290605.3300830.
  28. C Ilvento. Metric learning for individual fairness. Manuscript submitted for publication, 2019. Google Scholar
  29. Matthew Joseph, Michael Kearns, Jamie H Morgenstern, and Aaron Roth. Fairness in learning: Classic and contextual bandits. In Advances in Neural Information Processing Systems, pages 325-333, 2016. Google Scholar
  30. Christopher Jung, Michael Kearns, Seth Neel, Aaron Roth, Logan Stapleton, and Zhiwei Steven Wu. An algorithmic framework for fairness elicitation. arXiv preprint, 2019. URL: http://arxiv.org/abs/1905.10660.
  31. Anson Kahng, Min Kyung Lee, Ritesh Noothigattu, Ariel D. Procaccia, and Christos-Alexandros Psomas. Statistical foundations of virtual democracy. In Proceedings of the 36th International Conference on Machine Learning (ICML), pages 3173-3182, 2019. Google Scholar
  32. Faisal Kamiran and Toon Calders. Data preprocessing techniques for classification without discrimination. Knowledge and Information Systems, 33(1):1-33, 2012. Google Scholar
  33. Michael Kearns, Seth Neel, Aaron Roth, and Zhiwei Steven Wu. Preventing fairness gerrymandering: Auditing and learning for subgroup fairness. In International Conference on Machine Learning, pages 2569-2577, 2018. Google Scholar
  34. Michael J. Kearns, Seth Neel, Aaron Roth, and Zhiwei Steven Wu. Preventing fairness gerrymandering: Auditing and learning for subgroup fairness. In Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsmässan, Stockholm, Sweden, July 10-15, 2018, pages 2569-2577, 2018. URL: http://proceedings.mlr.press/v80/kearns18a.html.
  35. Michael Kim, Omer Reingold, and Guy Rothblum. Fairness through computationally-bounded awareness. In Advances in Neural Information Processing Systems, pages 4842-4852, 2018. Google Scholar
  36. Jyrki Kivinen and Manfred K. Warmuth. Exponentiated gradient versus gradient descent for linear predictors. Information and Computation, 132:1-63, 1997. Google Scholar
  37. Jon Kleinberg and Éva Tardos. Approximation algorithms for classification problems with pairwise relationships: metric labeling and markov random fields. In P40th Annual Symposium on Foundations of Computer Science, New York, NY, USA, pages 14 - -23, 1999. URL: https://doi.org/10.1109/SFFCS.1999.814572.
  38. James Konow. Is fairness in the eye of the beholder? an impartial spectator analysis of justice. Social Choice and Welfare, 33:101 - -127, 2009. Google Scholar
  39. Felicitas Kraemer, Kees van Overveld, and Martin Peterson. Is there an ethics of algorithms? Ethics and Information Technology, 13:251–-260, 2011. Google Scholar
  40. Bogdan Kulynych, David Madras, Smitha Milli, Inioluwa Deborah Raji, Angela Zhou, and Richard Zemel. Participatory approaches to machine learning. International Conference on Machine Learning Workshop, 2020. Google Scholar
  41. Preethi Lahoti, Krishna P. Gummadi, and Gerhard Weikum. Operationalizing individual fairness with pairwise fair representations. CoRR, abs/1907.01439, 2019. URL: http://arxiv.org/abs/1907.01439.
  42. Jeff Larson, Julia Angwin, Lauren Kirchner, and Surya Mattu. How we analyzed the compas recidivism algorithm, March 2019. URL: https://www.propublica.org/article/how-we-analyzed-the-compas-recidivism-algorithm.
  43. Min Kyung Lee. Understanding perception of algorithmic decisions: Fairness, trust, and emotion in response to algorithmic management. Big Data & Society, 5(1):2053951718756684, 2018. Google Scholar
  44. Min Kyung Lee and Su Baykal. Algorithmic mediation in group decisions: Fairness perceptions of algorithmically mediated vs. discussion-based social division. In Proceedings of the 2017 ACM Conference on Computer Supported Cooperative Work and Social Computing, pages 1035-1048. ACM, 2017. Google Scholar
  45. Min Kyung Lee, Ji Tae Kim, and Leah Lizarondo. A human-centered approach to algorithmic services: Considerations for fair and motivating smart community service management that allocates donations to non-profit organizations. In Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems, pages 3365-3376. ACM, 2017. Google Scholar
  46. Min Kyung Lee, Daniel Kusbit, Anson Kahng, Ji Tae Kim, Xinran Yuan, Allissa Chan, Daniel See, Ritesh Noothigattu, Siheon Lee, Alexandros Psomas, and Ariel D. Procaccia. Webuildai: Participatory framework for algorithmic governance. Proc. ACM Hum. Comput. Interact., 3(CSCW):181:1-181:35, 2019. Google Scholar
  47. John Monahan, Anne Metz, and Brandon L Garrett. Judicial appraisals of risk assessment in sentencing. Virginia Public Law and Legal Theory Research Paper, No. 2018-27, 2018. Google Scholar
  48. Arvind Narayanan. Translation tutorial: 21 fairness definitions and their politics. In Proc. Conf. Fairness Accountability Transp., New York, USA, 2018. Google Scholar
  49. Nam Nguyen and Rich Caruana. Improving classification with pairwise constraints: A margin-based approach. In Walter Daelemans, Bart Goethals, and Katharina Morik, editors, Machine Learning and Knowledge Discovery in Databases, pages 113-124, 2008. Google Scholar
  50. Noam Nisan. Introduction to mechanism design (for computer scientists). In N. Nisan, T. Roughgarden, E. Tardos, and V. Vazirani, editors, Algorithmic Game Theory. Cambridge University Press, 2007. Google Scholar
  51. Ritesh Noothigattu, Snehalkumar (Neil) S. Gaikwad, Edmond Awad, Sohan Dsouza, Iyad Rahwan, Pradeep Ravikumar, and Ariel D. Procaccia. A voting-based system for ethical decision making. In Proceedings of the 32nd Conference on Artificial Intelligence, (AAAI), pages 1587-1594, 2018. Google Scholar
  52. Gabriella Pigozzi, Alexis Tsoukiàs, and Paolo Viappiani. Preferences in artificial intelligence. Annals of Mathematics and Artificial Intelligence, 77:361-401, 2016. Google Scholar
  53. Guy N Rothblum and Gal Yona. Probably approximately metric-fair learning. arXiv preprint, 2018. URL: http://arxiv.org/abs/1803.03242.
  54. Debjani Saha, Candice Schumann, Duncan C. McElfresh, John P. Dickerson, Michelle L. Mazurek, and Michael Carl Tschantz. Measuring non-expert comprehension of machine learning fairness metrics. In Proceedings of the 37th International Conference on Machine Learning, ICML 2020, Vienna, Austria, July 12-18, 2020, 2020. Google Scholar
  55. Nripsuta Ani Saxena, Karen Huang, Evan DeFilippis, Goran Radanovic, David C. Parkes, and Yang Liu. 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, pages 99 - -106. ACM, 2019. Google Scholar
  56. Nicholas Scurich and John Monahan. Evidence-based sentencing: Public openness and opposition to using gender, age, and race as risk factors for recidivism. Law and Human Behavior, 40(1):36, 2016. Google Scholar
  57. Takuya Shimada, Han Bao, Issei Sato, and Masashi Sugiyama. Classification from pairwise similarities/dissimilarities and unlabeled data via empirical risk minimization. In Neural Computation, pages 1-35, 2021. URL: https://doi.org/10.1162/neco_a_01373.
  58. Maurice Sion et al. On general minimax theorems. Pacific Journal of mathematics, 8(1):171-176, 1958. Google Scholar
  59. Michael Veale, Max Van Kleek, and Reuben Binns. Fairness and accountability design needs for algorithmic support in high-stakes public sector decision-making. In Proceedings of the 2018 chi conference on human factors in computing systems, pages 1-14, 2018. Google Scholar
  60. Sahil Verma and Julia Rubin. Fairness definitions explained. In 2018 IEEE/ACM International Workshop on Software Fairness (FairWare), pages 1-7. IEEE, 2018. Google Scholar
  61. AJ Wang. Procedural justice and risk-assessment algorithms, 2018. URL: https://doi.org/10.2139/ssrn.3170136.
  62. Ruotong Wang, F Maxwell Harper, and Haiyi Zhu. Factors influencing perceived fairness in algorithmic decision-making: Algorithm outcomes, development procedures, and individual differences. In Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems, pages 1-14, 2020. Google Scholar
  63. Pak-Hang Wong. Democratizing algorithmic fairness. Philosophy & Technology, 33:225-244, 2020. Google Scholar
  64. Allison Woodruff, Sarah E Fox, Steven Rousso-Schindler, and Jeffrey Warshaw. A qualitative exploration of perceptions of algorithmic fairness. In Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems, page 656. ACM, 2018. Google Scholar
  65. Ariana Yaptangco. Male tennis pros confirm serena’s penalty was sexist and admit to saying worse on the court. Elle, 2017. URL: http://www.elle.com/culture/a23051870/male-tennis-pros-confirm-serenas-penalty-was-sexist-and-admit-to-saying-worse-on-the-court/.
  66. Muhammad Bilal Zafar, Isabel Valera, Manuel Gomez-Rodriguez, and Krishna P. Gummadi. Fairness beyond disparate treatment & disparate impact: Learning classification without disparate mistreatment. In Proceedings of the 26th International Conference on World Wide Web, WWW, pages 1171-1180. ACM, 2017. Google Scholar
  67. Rich Zemel, Yu Wu, Kevin Swersky, Toni Pitassi, and Cynthia Dwork. Learning fair representations. In International Conference on Machine Learning, pages 325-333, 2013. Google Scholar
  68. H. Zeng and Y. Cheung. Semi-supervised maximum margin clustering with pairwise constraints. IEEE Transactions on Knowledge and Data Engineering, 24(5):926-939, 2012. URL: https://doi.org/10.1109/TKDE.2011.68.
  69. Martin Zinkevich. Online convex programming and generalized infinitesimal gradient ascent. In Proceedings of the Twentieth International Conference on Machine Learning (ICML-2003), 2003. Google Scholar
Questions / Remarks / Feedback
X

Feedback for Dagstuhl Publishing


Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail
© 2023-2024 Schloss Dagstuhl – LZI GmbH Imprint Privacy Contact