학술논문
Can Ensembling Preprocessing Algorithms Lead to Better Machine Learning Fairness?
Document Type
Periodical
Author
Source
Computer. 56(4):71-79 Apr, 2023
Subject
Language
ISSN
0018-9162
1558-0814
1558-0814
Abstract
In this work, we evaluate three popular fairness preprocessing algorithms and investigate the potential for combining all algorithms into a more robust preprocessing ensemble. We report on lessons learned that can help practitioners better select fairness algorithms for their models.