Flexible Fairness Learning via Inverse Conditional Permutation

arXiv:2404.05678v1 Announce Type: cross
Abstract: Equalized odds, as a popular notion of algorithmic fairness, aims to ensure that sensitive variables, such as race and gender, do not unfairly influence the algorithm prediction when conditioning on the true outcome. Despite rapid advancements, most of the current research focuses on the violation of equalized odds caused by one sensitive attribute, leaving the challenge of simultaneously accounting for multiple attributes under-addressed. We address this gap by introducing a fairness learning approach that integrates …

abstract algorithm algorithmic fairness arxiv cs.cy cs.lg current fairness gender influence notion popular prediction race race and gender research stat.ml the algorithm true type variables via