A Maximal Correlation Framework for Fair Machine Learning
Author(s)
Lee, Joshua; Bu, Yuheng; Sattigeri, Prasanna; Panda, Rameswar; Wornell, Gregory W.; Karlinsky, Leonid; Schmidt Feris, Rogerio; ... Show more Show less
Downloadentropy-24-00461-v2.pdf (721.6Kb)
Publisher with Creative Commons License
Publisher with Creative Commons License
Creative Commons Attribution
Terms of use
Metadata
Show full item recordAbstract
As machine learning algorithms grow in popularity and diversify to many industries, ethical and legal concerns regarding their fairness have become increasingly relevant. We explore the problem of algorithmic fairness, taking an information–theoretic view. The maximal correlation framework is introduced for expressing fairness constraints and is shown to be capable of being used to derive regularizers that enforce independence and separation-based fairness criteria, which admit optimization algorithms for both discrete and continuous variables that are more computationally efficient than existing algorithms. We show that these algorithms provide smooth performance–fairness tradeoff curves and perform competitively with state-of-the-art methods on both discrete datasets (COMPAS, Adult) and continuous datasets (Communities and Crimes).
Date issued
2022-03Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science; MIT-IBM Watson AI LabJournal
Entropy
Publisher
MDPI AG
Citation
Entropy 24 (4): 461 (2022)
Version: Final published version
ISSN
1099-4300