Towards A Scalable Solution for Improving Multi-Group Fairness in Compositional Classification
This addresses fairness in complex multi-group, multi-label systems, which is an incremental improvement over existing fairness methods.
The paper tackled the problem of improving multi-group fairness in compositional classification systems, where existing methods scale poorly, and introduced two techniques that achieve constant scaling, demonstrating effectiveness in academic and real-world environments.
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 {\em task-overconditioning} and {\em 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.