2018

An Empirical Study of Rich Subgroup Fairness for Machine Learning

Kearns, Michael, Neel, Seth, Roth, Aaron et al.

Understand

Kearns et al.

[2018] recently proposed a notion of rich subgroup fairness intended to bridge the gap between statistical and individual notions of fairness.
Rich subgroup fairness picks a statistical fairness constraint (say, equalizing false positive rates across protected groups), but then asks that this constraint hold over an exponentially or infinitely large collection of subgroups defined by a class of functions with bounded VC dimension.
They give an algorithm guaranteed to learn subject to this constraint, under the condition that it has access to oracles for perfectly learning absent a fairness constraint.

Lsac national longitudinal bar passage study
L. Wightman · 1998
Earlier work this paper cites.
A data-driven software tool for enabling cooperative information sharing among police departments
M.A. Redmond and A. Baveja · 2002
Earlier work this paper cites.
Using data mining to predict secondary school student performance
P. Cortez and A. Silva · 2008
Earlier work this paper cites.
Three naive bayes approaches for discrimination-free classification
Toon Calders and Sicco Verwer · 2010
Earlier work this paper cites.
Fairness through awareness
Cynthia Dwork, Moritz Hardt, Toniann Pitassi, Omer Reingold, and Richard Zemel · 2012
Earlier work this paper cites.

Equality of opportunity in supervised learning
Moritz Hardt, Eric Price, and Nati Srebro · 2016
Cited alongside, same era.
Fair prediction with disparate impact: A study of bias in recidivism prediction instruments
Alexandra Chouldechova · 2017
Cited alongside, same era.
UCI machine learning repository , 2017
Dua Dheeru and Efi Karra Taniskidou · 2017
Cited alongside, same era.
Inherent trade-offs in the fair determination of risk scores
Jon M. Kleinberg, Sendhil Mullainathan, and Manish Raghavan · 2017
Cited alongside, same era.
A reductions approach to fair classification
Alekh Agarwal, Alina Beygelzimer, Miroslav Dudík, John Langford, and Hanna M. Wallach · 2018
Cited alongside, same era.
Multiaccuracy: Black-box post-processing for fairness in classification
Original
Michael P Kim, Amirata Ghorbani, and James Zou
Cited in the paper.
Fairness through computationally-bounded awareness
Original
Michael P Kim, Omer Reingold, and Guy N Rothblum
Cited in the paper.

Fairness in criminal justice risk assessments: The state of the art
Richard Berk, Hoda Heidari, Shahin Jabbari, Michael Kearns, and Aaron Roth · 2018
Closest in time.
Multicalibration: Calibration for the (computationally-identifiable) masses
Úrsula Hébert-Johnson, Michael P. Kim, Omer Reingold, and Guy N. Rothblum · 2018
Closest in time.
Preventing fairness gerrymandering: Auditing and learning for subgroup fairness
Michael J. Kearns, Seth Neel, Aaron Roth, and Zhiwei Steven Wu · 2018
Closest in time.
Learning non-discriminatory predictors
Blake Woodworth, Suriya Gunasekar, Mesrob I Ohannessian, and Nathan Srebro · 2018
Closest in time.

alphaXiv searches the wider corpus for related work and actual follow-ups.

alphaXiv is searching for related work…