ABSTRACT
Fairness for Machine Learning has received considerable attention, recently. Various mathematical formulations of fairness have been proposed, and it has been shown that it is impossible to satisfy all of them simultaneously. The literature so far has dealt with these impossibility results by quantifying the tradeoffs between different formulations of fairness. Our work takes a different perspective on this issue. Rather than requiring all notions of fairness to (partially) hold at the same time, we ask which one of them is the most appropriate given the societal domain in which the decision-making model is to be deployed. We take a descriptive approach and set out to identify the notion of fairness that best captures lay people's perception of fairness. We run adaptive experiments designed to pinpoint the most compatible notion of fairness with each participant's choices through a small number of tests. Perhaps surprisingly, we find that the most simplistic mathematical definition of fairness---namely, demographic parity---most closely matches people's idea of fairness in two distinct application scenarios. This conclusion remains intact even when we explicitly tell the participants about the alternative, more complicated definitions of fairness, and we reduce the cognitive burden of evaluating those notions for them. Our findings have important implications for the Fair ML literature and the discourse on formalizing algorithmic fairness.
- Julia Angwin, Jeff Larson, Surya Mattu, and Lauren Kirchner. 2016. Machine Bias. Propublica (2016).Google Scholar
- Edmond Awad, Sohan Dsouza, Richard Kim, Jonathan Schulz, Joseph Henrich, Azim Shariff, Jean-Francc ois Bonnefon, and Iyad Rahwan. 2018. The moral machine experiment. Nature , Vol. 563, 7729 (2018), 59.Google Scholar
- Anna Barry-Jester, Ben Casselman, and Dana Goldstein. 2015. The New Science of Sentencing. The Marshall Project (August 2015).Google Scholar
- Reuben Binns, Max Van Kleek, Michael Veale, Ulrik Lyngs, Jun Zhao, and Nigel Shadbolt. 2018. 'It's Reducing a Human Being to a Percentage': Perceptions of Justice in Algorithmic Decisions. In CHI. ACM, 377. Google ScholarDigital Library
- Joy Buolamwini and Timnit Gebru. 2018. Gender shades: Intersectional accuracy disparities in commercial gender classification. In In Proceedings of the 1st Conference on Fairness, Accountability and Transparency (FAT*). 77--91.Google Scholar
- Alexandra Chouldechova. 2017. Fair prediction with disparate impact: A study of bias in recidivism prediction instruments. arXiv preprint arXiv:1703.00056 (2017).Google Scholar
- Sam Corbett-Davies, Emma Pierson, Avi Feller, Sharad Goel, and Aziz Huq. 2017. Algorithmic decision making and the cost of fairness. In KDD. ACM, 797--806. Google ScholarDigital Library
- Rahul C. Deo. 2015. Machine learning in medicine. Circulation , Vol. 132, 20 (2015), 1920--1930.Google ScholarCross Ref
- 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 (ITCS). ACM, 214--226. Google ScholarDigital Library
- Michael Feldman, Sorelle A. Friedler, John Moeller, Carlos Scheidegger, and Suresh Venkatasubramanian. 2015. Certifying and removing disparate impact. In KDD. ACM, 259--268. Google ScholarDigital Library
- Pratik Gajane and Mykola Pechenizkiy. 2017. On formalizing fairness in prediction with machine learning. arXiv preprint arXiv:1710.03184 (2017).Google Scholar
- Daniel Golovin, Andreas Krause, and Debajyoti Ray. 2010. Near-optimal bayesian active learning with noisy observations. In NIPS . 766--774. Google ScholarDigital Library
- Nina Grgic-Hlaca, Elissa M. Redmiles, Krishna P Gummadi, and Adrian Weller. 2018. Human perceptions of fairness in algorithmic decision making: A case study of criminal risk prediction. In WWW. 903--912. Google ScholarDigital Library
- Moritz Hardt, Eric Price, and Nati Srebro. 2016. Equality of opportunity in supervised learning. In NIPS. 3315--3323. Google ScholarDigital Library
- Robert David Hart. 2017. If you're not a white male, artificial intelligence's use in healthcare could be dangerous. Quartz (July 2017).Google Scholar
- Hoda Heidari, Michele Loi, Krishna P. Gummadi, and Andreas Krause. 2019. A Moral Framework for Understanding of Fair ML through Economic Models of Equality of Opportunity. In FAT* . Google ScholarDigital Library
- Kenneth Holstein, Jennifer Wortman Vaughan, Hal Daumé III, Miro Dud'ik, and Hanna Wallach. 2018. Improving fairness in machine learning systems: What do industry practitioners need?. In CHI . Google ScholarDigital Library
- Matthew Joseph, Michael Kearns, Jamie Morgenstern, and Aaron Roth. 2016. Fairness in learning: Classic and contextual bandits. In NIPS. 325--333. Google ScholarDigital Library
- Jon Kleinberg, Sendhil Mullainathan, and Manish Raghavan. 2017. Inherent trade-offs in the fair determination of risk scores. In ITCS .Google Scholar
- Min Kyung Lee and Su Baykal. 2017. Algorithmic Mediation in Group Decisions: Fairness Perceptions of Algorithmically Mediated vs. Discussion-Based Social Division.. In CSCW. 1035--1048. Google ScholarDigital Library
- Min Kyung Lee, Daniel Kusbit, Anson Kahng, Ji Tae Kim, Xinran Yuan, Allissa Chan, Ritesh Noothigattu, Daniel See, Siheon Lee, and Christos-Alexandros Psomas. 2018. WeBuildAI: Participatory Framework for Fair and Efficient Algorithmic Governance.Google Scholar
- Ritesh Noothigattu, Snehalkumar 'Neil' S. Gaikwad, Edmond Awad, Sohan Dsouza, Iyad Rahwan, Pradeep Ravikumar, and Ariel D. Procaccia. 2018. A voting-based system for ethical decision making. In AAAI .Google Scholar
- Kevin Petrasic, Benjamin Saul, James Greig, and Matthew Bornfreund. 2017. Algorithms and bias: What lenders need to know. White & Case (2017).Google Scholar
- Debajyoti Ray, Daniel Golovin, Andreas Krause, and Colin Camerer. 2012. Bayesian rapid optimal adaptive design (broad): Method and application distinguishing models of risky choice. California Institute of Technology working paper (2012).Google Scholar
- Cynthia Rudin. 2013. Predictive Policing Using Machine Learning to Detect Patterns of Crime. Wired Magazine (August 2013). Retrieved 4/28/2016.Google Scholar
- Nripsuta Saxena, Karen Huang, Evan DeFilippis, Goran Radanovic, David Parkes, and Yang Liu. 2018. How Do Fairness Definitions Fare? Examining Public Attitudes Towards Algorithmic Definitions of Fairness. arXiv preprint arXiv:1811.03654 (2018). Google ScholarDigital Library
- 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 KDD . Google ScholarDigital Library
- Latanya Sweeney. 2013. Discrimination in online ad delivery. Queue , Vol. 11, 3 (2013), 10. Google ScholarDigital Library
- Anne Taylor and Jackson Wright. 2005. Importance of race/ethnicity in clinical trials. Circulation , Vol. 112, 23 (2005), 3654--3660.Google ScholarCross Ref
- Michael Veale, Max Van Kleek, and Reuben Binns. 2018. Fairness and Accountability Design Needs for Algorithmic Support in High-Stakes Public Sector Decision-Making. In CHI. ACM, 440. Google ScholarDigital Library
- Allison Woodruff, Sarah E. Fox, Steven Rousso-Schindler, and Jeffrey Warshaw. 2018. A Qualitative Exploration of Perceptions of Algorithmic Fairness. In CHI. ACM, 656. Google ScholarDigital Library
- 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 WWW. 1171--1180. Google ScholarDigital Library
Index Terms
- Mathematical Notions vs. Human Perception of Fairness: A Descriptive Approach to Fairness for Machine Learning
Recommendations
Airtime Fairness for IEEE 802.11 Multirate Networks
Under a multi rate network scenario, the IEEE 802.11 DCF MAC fails to provide air-time fairness for all competing stations since the protocol is designed for ensuring max-min throughput fairness and the maximum achievable throughput by any station gets ...
Machine learning fairness notions: Bridging the gap with real-world applications
AbstractFairness emerged as an important requirement to guarantee that Machine Learning (ML) predictive systems do not discriminate against specific individuals or entire sub-populations, in particular, minorities. Given the inherent ...
Highlights- A catalog of machine learning fairness notions.
- Machine learning fairness ...
Optimal CWmin selection for achieving proportional fairness in multi-rate 802.11e WLANs: test-bed implementation and evaluation
WiNTECH '06: Proceedings of the 1st international workshop on Wireless network testbeds, experimental evaluation & characterizationWe investigate the optimal selection of minimum contention window values to achieve proportional fairness in a multirate IEEE 802.11e test-bed. Unlike other approaches, the proposed model accounts for the contention-based nature of 802.11's MAC layer ...
Comments