Preventing fairness gerrymandering: Auditing and learning for subgroup fairness

Michael Kearns; Seth Neel; Aaron Roth; Zhiwei Steven Wu

Preventing fairness gerrymandering: Auditing and learning for subgroup fairness

Michael Kearns, Seth Neel, Aaron Roth, Zhiwei Steven Wu

Computer Science and Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

137 Scopus citations

Abstract

We introduce a new family of fairness definitions that interpolate between statistical and individual notions of fairness, obtaining some of the best properties of each. We show that checking whether these notions are satisfied is computationally hard in the worst case, but give practical oracle-efficient algorithms for learning subject to these constraints, and confirm our findings with experiments.

Original language	English (US)
Title of host publication	35th International Conference on Machine Learning, ICML 2018
Editors	Jennifer Dy, Andreas Krause
Publisher	International Machine Learning Society (IMLS)
Pages	4008-4016
Number of pages	9
ISBN (Electronic)	9781510867963
State	Published - 2018
Event	35th International Conference on Machine Learning, ICML 2018 - Stockholm, Sweden Duration: Jul 10 2018 → Jul 15 2018

Publication series

Name	35th International Conference on Machine Learning, ICML 2018
Volume	6

Other

Other	35th International Conference on Machine Learning, ICML 2018
Country/Territory	Sweden
City	Stockholm
Period	7/10/18 → 7/15/18

Bibliographical note

Publisher Copyright:
© CURRAN-CONFERENCE. All rights reserved.

Find It

Find It at U of M Libraries

Cite this

Preventing fairness gerrymandering: Auditing and learning for subgroup fairness. / Kearns, Michael; Neel, Seth; Roth, Aaron et al.
35th International Conference on Machine Learning, ICML 2018. ed. / Jennifer Dy; Andreas Krause. International Machine Learning Society (IMLS), 2018. p. 4008-4016 (35th International Conference on Machine Learning, ICML 2018; Vol. 6).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Kearns, M, Neel, S, Roth, A & Wu, ZS 2018, Preventing fairness gerrymandering: Auditing and learning for subgroup fairness. in J Dy & A Krause (eds), 35th International Conference on Machine Learning, ICML 2018. 35th International Conference on Machine Learning, ICML 2018, vol. 6, International Machine Learning Society (IMLS), pp. 4008-4016, 35th International Conference on Machine Learning, ICML 2018, Stockholm, Sweden, 7/10/18.

@inproceedings{7a6c14796bea4131bb0932c95e819e69,

title = "Preventing fairness gerrymandering: Auditing and learning for subgroup fairness",

abstract = "We introduce a new family of fairness definitions that interpolate between statistical and individual notions of fairness, obtaining some of the best properties of each. We show that checking whether these notions are satisfied is computationally hard in the worst case, but give practical oracle-efficient algorithms for learning subject to these constraints, and confirm our findings with experiments.",

author = "Michael Kearns and Seth Neel and Aaron Roth and Wu, {Zhiwei Steven}",

year = "2018",

language = "English (US)",

series = "35th International Conference on Machine Learning, ICML 2018",

publisher = "International Machine Learning Society (IMLS)",

pages = "4008--4016",

editor = "Jennifer Dy and Andreas Krause",

booktitle = "35th International Conference on Machine Learning, ICML 2018",

}

TY - GEN

T1 - Preventing fairness gerrymandering

T2 - 35th International Conference on Machine Learning, ICML 2018

AU - Kearns, Michael

AU - Neel, Seth

AU - Roth, Aaron

AU - Wu, Zhiwei Steven

PY - 2018

Y1 - 2018

N2 - We introduce a new family of fairness definitions that interpolate between statistical and individual notions of fairness, obtaining some of the best properties of each. We show that checking whether these notions are satisfied is computationally hard in the worst case, but give practical oracle-efficient algorithms for learning subject to these constraints, and confirm our findings with experiments.

AB - We introduce a new family of fairness definitions that interpolate between statistical and individual notions of fairness, obtaining some of the best properties of each. We show that checking whether these notions are satisfied is computationally hard in the worst case, but give practical oracle-efficient algorithms for learning subject to these constraints, and confirm our findings with experiments.

UR - http://www.scopus.com/inward/record.url?scp=85057263888&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85057263888&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85057263888

T3 - 35th International Conference on Machine Learning, ICML 2018

SP - 4008

EP - 4016

BT - 35th International Conference on Machine Learning, ICML 2018

A2 - Dy, Jennifer

A2 - Krause, Andreas

PB - International Machine Learning Society (IMLS)

Y2 - 10 July 2018 through 15 July 2018

ER -

Preventing fairness gerrymandering: Auditing and learning for subgroup fairness

Abstract

Publication series

Other

Bibliographical note

Find It

Other files and links

Fingerprint

Cite this