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 \textit{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.
Cite
Text
Schrouff et al. "Diagnosing Failures of Fairness Transfer Across Distribution Shift in Real-World Medical Settings." Neural Information Processing Systems, 2022.Markdown
[Schrouff et al. "Diagnosing Failures of Fairness Transfer Across Distribution Shift in Real-World Medical Settings." Neural Information Processing Systems, 2022.](https://mlanthology.org/neurips/2022/schrouff2022neurips-diagnosing/)BibTeX
@inproceedings{schrouff2022neurips-diagnosing,
title = {{Diagnosing Failures of Fairness Transfer Across Distribution Shift in Real-World Medical Settings}},
author = {Schrouff, Jessica and Harris, Natalie and Koyejo, Sanmi and Alabdulmohsin, Ibrahim M and Schnider, Eva and Opsahl-Ong, Krista and Brown, Alexander and Roy, Subhrajit and Mincu, Diana and Chen, Christina and Dieng, Awa and Liu, Yuan and Natarajan, Vivek and Karthikesalingam, Alan and Heller, Katherine A. and Chiappa, Silvia and D'Amour, Alexander},
booktitle = {Neural Information Processing Systems},
year = {2022},
url = {https://mlanthology.org/neurips/2022/schrouff2022neurips-diagnosing/}
}