Enforcing Delayed-Impact Fairness Guarantees

Recent research has shown that seemingly fair machine learning models, when used to inform decisions that have an impact on peoples' lives or well-being (e.g., applications involving education, employment, and lending), can inadvertently increase social inequality in the long term. This is beca...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2022-08
Main Authors: Weber, Aline, Metevier, Blossom, Brun, Yuriy, Thomas, Philip S, Bruno Castro da Silva
Format: Article
Language:English
Subjects:
Algorithms
Machine learning
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Recent research has shown that seemingly fair machine learning models, when used to inform decisions that have an impact on peoples' lives or well-being (e.g., applications involving education, employment, and lending), can inadvertently increase social inequality in the long term. This is because prior fairness-aware algorithms only consider static fairness constraints, such as equal opportunity or demographic parity. However, enforcing constraints of this type may result in models that have negative long-term impact on disadvantaged individuals and communities. We introduce ELF (Enforcing Long-term Fairness), the first classification algorithm that provides high-confidence fairness guarantees in terms of long-term, or delayed, impact. We prove that the probability that ELF returns an unfair solution is less than a user-specified tolerance and that (under mild assumptions), given sufficient training data, ELF is able to find and return a fair solution if one exists. We show experimentally that our algorithm can successfully mitigate long-term unfairness.
ISSN:2331-8422