keynote

Inherent Trade-Offs in Algorithmic Fairness

Author:

Jon KleinbergAuthors Info & Claims

SIGMETRICS '18: Abstracts of the 2018 ACM International Conference on Measurement and Modeling of Computer Systems

Page 40

https://doi.org/10.1145/3219617.3219634

Published: 12 June 2018 Publication History

Get Access

Abstract

Recent discussion in both the academic literature and the public sphere about classification by algorithms has involved tension between competing notions of what it means for such a classification to be fair to different groups. We consider several of the key fairness conditions that lie at the heart of these debates, and discuss recent research establishing inherent trade-offs between these conditions. We also consider a variety of methods for promoting fairness and related notions for classification and selection problems that involve sets rather than just individuals.

References

[1]

Julia Angwin, Jeff Larson, Surya Mattu, and Lauren Kirchner. May 23, 2016. Machine Bias: There's software used across the country to predict future criminals. And it's biased against blacks. ProPublica (. May 23, 2016). https://www.propublica.org/article/machine-bias-risk-assessments-in-criminal-sentencing.

Google Scholar

[2]

Solon Barocas and Andrew D Selbst. 2016. Big data's disparate impact. California Law Review Vol. 104 (2016).

Google Scholar

[3]

Alexandra Chouldechova. 2017. Fair prediction with disparate impact: A study of bias in recidivism prediction instruments. Big Data (2017).

Google Scholar

[4]

Sam Corbett-Davies, Emma Pierson, Avi Feller, Sharad Goel, and Aziz Huq. 2017. Algorithmic Decision Making and the Cost of Fairness Proceedings of the 23rd Conference on Knowledge Discovery and Data Mining (KDD).

Digital Library

Google Scholar

[5]

Cynthia Dwork, Moritz Hardt, Toniann Pitassi, Omer Reingold, and Richard S. Zemel. 2012. Fairness through awareness. In Innovations in Theoretical Computer Science 2012, Cambridge, MA, USA, January 8--10, 2012. 214--226.

Digital Library

Google Scholar

[6]

Michael Feldman, Sorelle A. Friedler, John Moeller, Carlos Scheidegger, and Suresh Venkatasubramanian. 2015. Certifying and Removing Disparate Impact. In Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD '15). ACM, New York, NY, USA, 259--268.

Digital Library

Google Scholar

[7]

Anthony Flores, Christopher Lowenkamp, and Kristin Bechtel. 2016. False Positives, False Negatives, and False Analyses: A Rejoinder to “Machine Bias: There's Software Used Across the Country to Predict Future Criminals. And it's Biased Against Blacks.”. Technical Report. Crime & Justice Institute. http://www.crj.org/cji/entry/false-positives-false-negatives-and-false-analyses-a-rejoinder.

Google Scholar

[8]

Moritz Hardt, Eric Price, and Nathan Srebro. 2016. Equality of Opportunity in Supervised Learning. In Advances in Neural Information Processing Systems.

Digital Library

Google Scholar

[9]

Lu Hong and Scott E. Page. 2004. Groups of diverse problem solvers can outperform groups of high-ability problem solvers. Proceedings of the National Academy of Sciences Vol. 101, 46 (Nov 16. 2004), 16385--16398.

Crossref

Google Scholar

[10]

Jon M. Kleinberg, Sendhil Mullainathan, and Manish Raghavan. 2017. Inherent Trade-Offs in the Fair Determination of Risk Scores 8th Innovations in Theoretical Computer Science Conference, ITCS 2017, January 9--11, 2017, Berkeley, CA, USA. 43:1--43:23.

Google Scholar

[11]

Jon M. Kleinberg and Manish Raghavan. 2018. Selection Problems in the Presence of Implicit Bias 9th Innovations in Theoretical Computer Science Conference, ITCS 2018, January 11--14, 2018, Cambridge, MA, USA. 33:1--33:17.

Google Scholar

[12]

Jon M. Kleinberg and Maithra Raghu. 2015. Team Performance with Test Scores. In Proceedings of the Sixteenth ACM Conference on Economics and Computation, EC '15, Portland, OR, USA, June 15--19, 2015. 511--528.

Digital Library

Google Scholar

[13]

Scott E. Page. 2008. The Difference: How the Power of Diversity Creates Better Groups, Firms, Schools, and Societies. Princeton University Press.

Digital Library

Google Scholar

[14]

Geoff Pleiss, Manish Raghavan, Felix Wu, Jon M. Kleinberg, and Kilian Q. Weinberger. 2017. On Fairness and Calibration. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 4--9 December 2017, Long Beach, CA, USA. 5684--5693. http://papers.nips.cc/paper/7151-on-fairness-and-calibration

Google Scholar

Cited By

View all

Kaur DHughes JRogers AKang GNarayan SAshley EPerez M(2024)Race, Sex, and Age Disparities in the Performance of ECG Deep Learning Models Predicting Heart FailureCirculation: Heart Failure10.1161/CIRCHEARTFAILURE.123.01087917:1Online publication date: Jan-2024
https://doi.org/10.1161/CIRCHEARTFAILURE.123.010879
Trotter CChen YLo DGamess E(2024)Exploring Fairness-Accuracy Trade-Offs in Binary Classification: A Comparative Analysis Using Modified Loss FunctionsProceedings of the 2024 ACM Southeast Conference10.1145/3603287.3651192(148-156)Online publication date: 18-Apr-2024
https://dl.acm.org/doi/10.1145/3603287.3651192
Alfiani FSantiago F(2024)A Comparative Analysis of Artificial Intelligence Regulatory Law in Asia, Europe, and AmericaSHS Web of Conferences10.1051/shsconf/202420407006204(07006)Online publication date: 25-Nov-2024
https://doi.org/10.1051/shsconf/202420407006
Show More Cited By

Index Terms

Inherent Trade-Offs in Algorithmic Fairness
1. Applied computing
  1. Law, social and behavioral sciences
2. Theory of computation
  1. Design and analysis of algorithms
    1. Algorithm design techniques

Recommendations

Inherent Trade-Offs in Algorithmic Fairness
SIGMETRICS '18

Recent discussion in both the academic literature and the public sphere about classification by algorithms has involved tension between competing notions of what it means for such a classification to be fair to different groups. We consider several of ...
Algorithmic Fairness in Mortgage Lending: from Absolute Conditions to Relational Trade-offs
Abstract
To address the rising concern that algorithmic decision-making may reinforce discriminatory biases, researchers have proposed many notions of fairness and corresponding mathematical formalizations. Each of these notions is often presented as a one-...
Algorithmic Fairness and Structural Injustice: Insights from Feminist Political Philosophy
AIES '22: Proceedings of the 2022 AAAI/ACM Conference on AI, Ethics, and Society

Data-driven predictive algorithms are widely used to automate and guide high-stake decision making such as bail and parole recommendation, medical resource distribution, and mortgage allocation. Nevertheless, harmful outcomes biased against vulnerable ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

SIGMETRICS '18: Abstracts of the 2018 ACM International Conference on Measurement and Modeling of Computer Systems

June 2018

155 pages

ISBN:9781450358460

DOI:10.1145/3219617

General Chair:
Konstantinos Psounis
University of Southern California
,
Program Chairs:
Aditya Akella
University of Wisconsin-Madison
,
Adam Wierman
California Institute of Technology

ACM SIGMETRICS Performance Evaluation Review Volume 46, Issue 1
SIGMETRICS '18
June 2018
142 pages
ISSN:0163-5999
DOI:10.1145/3292040
Editor:
Nidhi Hegde
Borealis AI
Issue’s Table of Contents

Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for third-party components of this work must be honored. For all other uses, contact the Owner/Author.

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 12 June 2018

Check for updates

Author Tags

Qualifiers

Keynote

Funding Sources

Simons Foundation

Conference

SIGMETRICS '18

Sponsor:

SIGMETRICS

SIGMETRICS '18: ACM SIGMETRICS / International Conference on Measurement and Modeling of Computer Systems

June 18 - 22, 2018

CA, Irvine, USA

Acceptance Rates

SIGMETRICS '18 Paper Acceptance Rate 54 of 270 submissions, 20%;

Overall Acceptance Rate 459 of 2,691 submissions, 17%

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

90
Total Citations
View Citations
1,454
Total Downloads

Downloads (Last 12 months)121
Downloads (Last 6 weeks)16

Reflects downloads up to 11 Dec 2024

Other Metrics

View Author Metrics

Citations

Cited By

View all

Kaur DHughes JRogers AKang GNarayan SAshley EPerez M(2024)Race, Sex, and Age Disparities in the Performance of ECG Deep Learning Models Predicting Heart FailureCirculation: Heart Failure10.1161/CIRCHEARTFAILURE.123.01087917:1Online publication date: Jan-2024
https://doi.org/10.1161/CIRCHEARTFAILURE.123.010879
Trotter CChen YLo DGamess E(2024)Exploring Fairness-Accuracy Trade-Offs in Binary Classification: A Comparative Analysis Using Modified Loss FunctionsProceedings of the 2024 ACM Southeast Conference10.1145/3603287.3651192(148-156)Online publication date: 18-Apr-2024
https://dl.acm.org/doi/10.1145/3603287.3651192
Alfiani FSantiago F(2024)A Comparative Analysis of Artificial Intelligence Regulatory Law in Asia, Europe, and AmericaSHS Web of Conferences10.1051/shsconf/202420407006204(07006)Online publication date: 25-Nov-2024
https://doi.org/10.1051/shsconf/202420407006
Lotter W(2024)Acquisition parameters influence AI recognition of race in chest x-rays and mitigating these factors reduces underdiagnosis biasNature Communications10.1038/s41467-024-52003-315:1Online publication date: 29-Aug-2024
https://doi.org/10.1038/s41467-024-52003-3
Alateeq MPedrycz W(2024)Logic-oriented fuzzy neural networks: A surveyExpert Systems with Applications10.1016/j.eswa.2024.125120(125120)Online publication date: Aug-2024
https://doi.org/10.1016/j.eswa.2024.125120
Dablain DKrawczyk BChawla N(2024)Towards a holistic view of bias in machine learning: bridging algorithmic fairness and imbalanced learningDiscover Data10.1007/s44248-024-00007-12:1Online publication date: 4-Apr-2024
https://doi.org/10.1007/s44248-024-00007-1
Cresto E(2024)Knowledge, algorithmic predictions, and actionAsian Journal of Philosophy10.1007/s44204-024-00172-93:2Online publication date: 21-Jun-2024
https://doi.org/10.1007/s44204-024-00172-9
Suri GKaur GShinde D(2024)Beyond boundaries: exploring the transformative power of AI in pharmaceuticalsDiscover Artificial Intelligence10.1007/s44163-024-00192-74:1Online publication date: 14-Nov-2024
https://doi.org/10.1007/s44163-024-00192-7
Orwat CBareis JFolberth AJahnel JWadephul C(2024)Normative Challenges of Risk Regulation of Artificial IntelligenceNanoEthics10.1007/s11569-024-00454-918:2Online publication date: 23-Aug-2024
https://doi.org/10.1007/s11569-024-00454-9
Prunkl C(2024)Human Autonomy at Risk? An Analysis of the Challenges from AIMinds and Machines10.1007/s11023-024-09665-134:3Online publication date: 24-Jun-2024
https://doi.org/10.1007/s11023-024-09665-1
Show More Cited By

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Cited By

Index Terms

Recommendations

Inherent Trade-Offs in Algorithmic Fairness

Algorithmic Fairness in Mortgage Lending: from Absolute Conditions to Relational Trade-offs

Algorithmic Fairness and Structural Injustice: Insights from Feminist Political Philosophy