Protecting the Protected Group: Circumventing Harmful Fairness

Machine Learning (ML) algorithms shape our lives. Banks use them to determine if we are good borrowers; IT companies delegate them recruitment decisions; police apply ML for crime-prediction, and judges base their verdicts on ML. However, real-world examples show that such automated decisions tend to discriminate against protected groups. This potential discrimination generated a huge hype both in media and in the research community. Quite a few formal notions of fairness were proposed, which take a form of constraints a "fair" algorithm must satisfy. We focus on scenarios where fairness is imposed on a self-interested party (e.g., a bank that maximizes its revenue). We find that the disadvantaged protected group can be worse off after imposing a fairness constraint. We introduce a family of \textit{Welfare-Equalizing} fairness constraints that equalize per-capita welfare of protected groups, and include \textit{Demographic Parity} and \textit{Equal Opportunity} as particular cases. In this family, we characterize conditions under which the fairness constraint helps the disadvantaged group. We also characterize the structure of the optimal \textit{Welfare-Equalizing} classifier for the self-interested party, and provide an algorithm to compute it. Overall, our \textit{Welfare-Equalizing} fairness approach provides a unified framework for discussing fairness in classification in the presence of a self-interested party.

[1]  E. Kalai,et al.  OTHER SOLUTIONS TO NASH'S BARGAINING PROBLEM , 1975 .

[2]  丸山 徹 Convex Analysisの二,三の進展について , 1977 .

[3]  Elisha A. Pazner,et al.  Egalitarian Equivalent Allocations: A New Concept of Economic Equity , 1978 .

[4]  D. Whittaker,et al.  A Course in Functional Analysis , 1991, The Mathematical Gazette.

[5]  J. Roemer Equality of Resources Implies Equality of Welfare , 1986 .

[6]  Debraj Ray,et al.  A Concept of Egalitarianism under Participation Constraints , 1989 .

[7]  Venkatesan Guruswami,et al.  On profit-maximizing envy-free pricing , 2005, SODA '05.

[8]  Ioannis Caragiannis,et al.  The Efficiency of Fair Division , 2009, Theory of Computing Systems.

[9]  Dimitris Bertsimas,et al.  The Price of Fairness , 2011, Oper. Res..

[10]  Ariel D. Procaccia,et al.  Optimal Envy-Free Cake Cutting , 2011, AAAI.

[11]  Toniann Pitassi,et al.  Fairness through awareness , 2011, ITCS '12.

[12]  Jin Li,et al.  Egalitarian division under Leontief Preferences , 2013 .

[13]  Lawrence G. Sager Handbook of Computational Social Choice , 2015 .

[14]  Jennifer L. Doleac,et al.  Does “Ban the Box” Help or Hurt Low-Skilled Workers? Statistical Discrimination and Employment Outcomes When Criminal Histories are Hidden , 2016 .

[15]  Cathy O'Neil,et al.  Weapons of Math Destruction: How Big Data Increases Inequality and Threatens Democracy , 2016, Vikalpa: The Journal for Decision Makers.

[16]  Ariel D. Procaccia,et al.  The Unreasonable Fairness of Maximum Nash Welfare , 2016, EC.

[17]  Ya'akov Gal,et al.  Which is the fairest (rent division) of them all? , 2017, IJCAI.

[18]  Karin Rothschild,et al.  A Course In Functional Analysis , 2016 .

[19]  Cathy O'Neil Weapons of Math Destruction , 2016 .

[20]  Nathan Srebro,et al.  Equality of Opportunity in Supervised Learning , 2016, NIPS.

[21]  Matt J. Kusner,et al.  Counterfactual Fairness , 2017, NIPS.

[22]  Tony Doyle,et al.  Weapons of Math Destruction: How Big Data Increases Inequality and Threatens Democracy , 2017, Inf. Soc..

[23]  Sergei Vassilvitskii,et al.  Revenue Optimization with Approximate Bid Predictions , 2017, NIPS.

[24]  Avi Feller,et al.  Algorithmic Decision Making and the Cost of Fairness , 2017, KDD.

[25]  Dan W. Brockt,et al.  The Theory of Justice , 2017 .

[26]  Krishna P. Gummadi,et al.  From Parity to Preference-based Notions of Fairness in Classification , 2017, NIPS.

[27]  Jon M. Kleinberg,et al.  Inherent Trade-Offs in the Fair Determination of Risk Scores , 2016, ITCS.

[28]  Ariel D. Procaccia,et al.  How to Make Envy Vanish Over Time , 2018, EC.

[29]  Timnit Gebru,et al.  Gender Shades: Intersectional Accuracy Disparities in Commercial Gender Classification , 2018, FAT.

[30]  John Langford,et al.  A Reductions Approach to Fair Classification , 2018, ICML.

[31]  Adam Tauman Kalai,et al.  Decoupled Classifiers for Group-Fair and Efficient Machine Learning , 2017, FAT.

[32]  G. Meyers,et al.  Enacting Actuarial Fairness in Insurance: From Fair Discrimination to Behaviour-based Fairness , 2018 .

[33]  Esther Rolf,et al.  Delayed Impact of Fair Machine Learning , 2018, ICML.

[34]  Google,et al.  Improving Online Algorithms via ML Predictions , 2024, NeurIPS.

[35]  Sergei Vassilvitskii,et al.  Competitive caching with machine learned advice , 2018, ICML.

[36]  Tim Roughgarden,et al.  Almost Envy-Freeness with General Valuations , 2017, SODA.

[37]  Sharad Goel,et al.  The Measure and Mismeasure of Fairness: A Critical Review of Fair Machine Learning , 2018, ArXiv.

[38]  Thomas S. Woodson Weapons of math destruction , 2018, Journal of Responsible Innovation.

[39]  Krishna P. Gummadi,et al.  Fairness Behind a Veil of Ignorance: A Welfare Analysis for Automated Decision Making , 2018, NeurIPS.

[40]  Sreenivas Gollapudi,et al.  Online Algorithms for Rent-Or-Buy with Expert Advice , 2019, ICML.

[41]  Ariel D. Procaccia,et al.  Paradoxes in Fair Machine Learning , 2019, NeurIPS.

[42]  Maria-Florina Balcan,et al.  Envy-Free Classification , 2018, NeurIPS.

[43]  David C. Parkes,et al.  Fairness without Harm: Decoupled Classifiers with Preference Guarantees , 2019, ICML.

[44]  Krishna P. Gummadi,et al.  A Moral Framework for Understanding of Fair ML through Economic Models of Equality of Opportunity , 2018, ArXiv.

[45]  Sendhil Mullainathan,et al.  An Economic Approach to Regulating Algorithms , 2020, SSRN Electronic Journal.

[46]  Benjamin Fish,et al.  The effects of competition and regulation on error inequality in data-driven markets , 2020, FAT*.

[47]  Yiling Chen,et al.  Fair classification and social welfare , 2019, FAT*.

[48]  Jon Kleinberg,et al.  An Economic Perspective on Algorithmic Fairness , 2020 .

[49]  Nisarg Shah,et al.  Designing Fairly Fair Classifiers Via Economic Fairness Notions , 2020, WWW.