Towards A Scalable Solution for Improving Multi-Group Fairness in Compositional Classification
Keywords: Responsible, Machine, Learning, Equal, Opportunity, Scalable, Classification
TL;DR: We show that baseline approaches to inducing equality of opportunity in classifiers scale poorly in the number of prediction tasks and number of groups remediated and propose a new technique with constant scaling in those dimensions
Abstract: Despite the rich literature on machine learning fairness, relatively little attention has been paid to remediating complex systems, where the final prediction is the combination of multiple classifiers and where multiple groups are present. In this paper, we first show that natural baseline approaches for improving equal opportunity fairness scale linearly with the product of the number of remediated groups and the number of remediated prediction labels, rendering them impractical. We then introduce two simple techniques, called task-overconditioning and group-interleaving, to achieve a constant scaling in this multi-group multi-label setup. Our experimental results in academic and real-world environments demonstrate the effectiveness of our proposal at mitigation within this environment.
Submission Number: 47
Loading