Research

SenSeI: Sensitive Set Invariance for Enforcing Individual Fairness

ICLR

Authors

Published on

06/25/2020

Categories

ICLR Machine Learning

In this paper, we cast fair machine learning as invariant machine learning. We first formulate a version of individual fairness that enforces invariance on certain sensitive sets. We then design a transport-based regularizer that enforces this version of individual fairness and develop an algorithm to minimize the regularizer efficiently. Our theoretical results guarantee the proposed approach trains certifiably fair ML models. Finally, in the experimental studies we demonstrate improved fairness metrics in comparison to several recent fair training procedures on three ML tasks that are susceptible to algorithmic bias.

This paper has been published at ICLR 2021

Please cite our work using the BibTeX below.

@misc{yurochkin2021sensei,
      title={SenSeI: Sensitive Set Invariance for Enforcing Individual Fairness}, 
      author={Mikhail Yurochkin and Yuekai Sun},
      year={2021},
      eprint={2006.14168},
      archivePrefix={arXiv},
      primaryClass={cs.LG}
}
Close Modal