Diagnosing failures of fairness transfer across distribution shift in real-world medical settings
Abstract
Diagnosing and mitigating changes in model fairness under distribution shift is an important component of the safe deployment of machine learning in healthcare settings. Importantly, the success of any mitigation strategy strongly depends on the structure of the shift. Despite this, there has been little discussion of how to empirically assess the structure of a distribution shift that one is encountering in practice. In this work, we adopt a causal framing to motivate conditional independence tests as a key tool for characterizing distribution shifts. Using our approach in two medical applications, we show that this knowledge can help diagnose failures of fairness transfer, including cases where real-world shifts are more complex than is often assumed in the literature. Based on these results, we discuss potential remedies at each step of the machine learning pipeline.
Keywords
Cite
@article{arxiv.2202.01034,
title = {Diagnosing failures of fairness transfer across distribution shift in real-world medical settings},
author = {Jessica Schrouff and Natalie Harris and Oluwasanmi Koyejo and Ibrahim Alabdulmohsin and Eva Schnider and Krista Opsahl-Ong and Alex Brown and Subhrajit Roy and Diana Mincu and Christina Chen and Awa Dieng and Yuan Liu and Vivek Natarajan and Alan Karthikesalingam and Katherine Heller and Silvia Chiappa and Alexander D'Amour},
journal= {arXiv preprint arXiv:2202.01034},
year = {2023}
}