Envy-Free Classification

In classic fair division problems such as cake cutting and rent division, envy-freeness requires that each individual (weakly) prefer his allocation to anyone else's. On a conceptual level, we argue that envy-freeness also provides a compelling notion of fairness for classification tasks. Our technical focus is the generalizability of envy-free classification, i.e., understanding whether a classifier that is envy free on a sample would be almost envy free with respect to the underlying distribution with high probability. Our main result establishes that a small sample is sufficient to achieve such guarantees, when the classifier in question is a mixture of deterministic classifiers that belong to a family of low Natarajan dimension.

[1]  D. Foley.  Resource allocation and the public sector , 1967 .

[2]  Vladimir Vapnik,et al.  Chervonenkis: On the uniform convergence of relative frequencies of events to their probabilities , 1971 .

[3]  H. Varian.  Equity, Envy and Efficiency , 1974 .

[4]  Andrew Chi-Chih Yao,et al.  Probabilistic computations: Toward a unified measure of complexity , 1977, 18th Annual Symposium on Foundations of Computer Science (sfcs 1977).

[5]  Balas K. Natarajan,et al.  On learning sets and functions , 2004, Machine Learning.

[6]  Steven J. Brams,et al.  Fair division - from cake-cutting to dispute resolution , 1998 .

[7]  Jack M. Robertson,et al.  Cake-cutting algorithms - be fair if you can , 1998 .

[8]  F. Su.  Rental Harmony: Sperner's Lemma in Fair Division , 1999 .

[9]  Daphne Koller,et al.  Learning an Agent's Utility Function by Observing Behavior , 2001, ICML.

[10]  Hervé Moulin,et al.  Fair division and collective welfare , 2003 .

[11]  Thomas D. Nielsen,et al.  Learning a decision maker's utility function from (possibly) inconsistent behavior , 2004, Artif. Intell..

[12]  Franco Turini,et al.  k-NN as an implementation of situation testing for discrimination discovery and prevention , 2011, KDD.

[13]  Maria-Florina Balcan,et al.  Learning Valuation Functions , 2011, COLT.

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

[15]  Amit Daniely,et al.  Multiclass Learning Approaches: A Theoretical Comparison with Implications , 2012, NIPS.

[16]  Toniann Pitassi,et al.  Learning Fair Representations , 2013, ICML.

[17]  Latanya Sweeney,et al.  Discrimination in online ad delivery , 2013, CACM.

[18]  Ariel D. Procaccia,et al.  Cake cutting: not just child's play , 2013, CACM.

[19]  David C. Parkes,et al.  Computing Parametric Ranking Models via Rank-Breaking , 2014, ICML.

[20]  Michael Carl Tschantz,et al.  Automated Experiments on Ad Privacy Settings: A Tale of Opacity, Choice, and Discrimination , 2014, ArXiv.

[21]  Shai Ben-David,et al.  Understanding Machine Learning: From Theory to Algorithms , 2014 .

[22]  Carlos Eduardo Scheidegger,et al.  Certifying and Removing Disparate Impact , 2014, KDD.

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

[24]  Aaron Roth,et al.  Fairness in Learning: Classic and Contextual Bandits , 2016, NIPS.

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

[26]  Stephen P. Boyd,et al.  CVXPY: A Python-Embedded Modeling Language for Convex Optimization , 2016, J. Mach. Learn. Res..

[27]  Pasin Manurangsi,et al.  Asymptotic existence of fair divisions for groups , 2017, Math. Soc. Sci..

[28]  Guy N. Rothblum,et al.  Calibration for the (Computationally-Identifiable) Masses , 2017, ArXiv.

[29]  Krishna P. Gummadi,et al.  Fairness Constraints: Mechanisms for Fair Classification , 2015, AISTATS.

[30]  Nathan Srebro,et al.  Learning Non-Discriminatory Predictors , 2017, COLT.

[31]  Stephen Boyd,et al.  A Rewriting System for Convex Optimization Problems , 2017, ArXiv.

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

[33]  Bernhard Schölkopf,et al.  Avoiding Discrimination through Causal Reasoning , 2017, NIPS.

[34]  Shai Ben-David,et al.  Empirical Risk Minimization under Fairness Constraints , 2018, NeurIPS.

[35]  Iyad Rahwan,et al.  A Voting-Based System for Ethical Decision Making , 2017, AAAI.

[36]  Guy N. Rothblum,et al.  Probably Approximately Metric-Fair Learning , 2018, ICML.

[37]  Vincent Conitzer,et al.  Adapting a Kidney Exchange Algorithm to Align with Human Values , 2018, AAAI.

[38]  Equity , 2020 .