Paired-Consistency: An example-based model-agnostic approach to fairness regularization in machine learning

Yair Horesh*, Noa Haas, Elhanan Mishraky, Yehezkel S. Resheff, Shir Meir Lador

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

6 Scopus citations

Abstract

As AI systems develop in complexity it is becoming increasingly hard to ensure non-discrimination on the basis of protected attributes such as gender, age, and race. Many recent methods have been developed for dealing with this issue as long as the protected attribute is explicitly available for the algorithm. We address the setting where this is not the case (with either no explicit protected attribute, or a large set of them). Instead, we assume the existence of a fair domain expert capable of generating an extension to the labeled dataset - a small set of example pairs, each having a different value on a subset of protected variables, but judged to warrant a similar model response. We define a performance metric - paired consistency. Paired consistency measures how close the output (assigned by a classifier or a regressor) is on these carefully selected pairs of examples for which fairness dictates identical decisions. In some cases consistency can be embedded within the loss function during optimization and serve as a fairness regularizer, and in others it is a tool for fair model selection. We demonstrate our method using the well studied Income Census dataset.

Original languageAmerican English
Title of host publicationMachine Learning and Knowledge Discovery in Databases - International Workshops of ECML PKDD 2019, Proceedings
EditorsPeggy Cellier, Kurt Driessens
PublisherSpringer
Pages590-604
Number of pages15
ISBN (Print)9783030438227
DOIs
StatePublished - 2020
Externally publishedYes
Event19th Joint European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, ECML PKDD 2019 - Wurzburg, Germany
Duration: 16 Sep 201920 Sep 2019

Publication series

NameCommunications in Computer and Information Science
Volume1167 CCIS
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference19th Joint European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, ECML PKDD 2019
Country/TerritoryGermany
CityWurzburg
Period16/09/1920/09/19

Bibliographical note

Publisher Copyright:
© Springer Nature Switzerland AG 2020.

Keywords

  • AI
  • Fairness
  • Machine learning
  • Social responsibility

Fingerprint

Dive into the research topics of 'Paired-Consistency: An example-based model-agnostic approach to fairness regularization in machine learning'. Together they form a unique fingerprint.

Cite this