A Maximal Correlation Framework for Fair Machine Learning
Name
entropy-24-00461-v2.pdf
Size
721.65 KB
Format
Unknown
Checksum (MD5)
0642f816547c9c51f50fbb570257b5b9
Author(s)
Lee, Joshua
Bu, Yuheng
Sattigeri, Prasanna
Panda, Rameswar
Wornell, Gregory W.
Karlinsky, Leonid
Schmidt Feris, Rogerio
Date Issued
March 2022
Journal
Entropy
Publisher
MDPI AG
Citation
Entropy 24 (4): 461 (2022)
Version
Final published version
Abstract
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).
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
MIT-IBM Watson AI Lab
Terms of Use
Creative Commons Attribution
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.3390/e24040461
