Hyper-parameter Tuning for Fair Classification without Sensitive Attribute Access

arXiv:2302.01385v2 Announce Type: replace
Abstract: Fair machine learning methods seek to train models that balance model performance across demographic subgroups defined over sensitive attributes like race and gender. Although sensitive attributes are typically assumed to be known during training, they may not be available in practice due to privacy and other logistical concerns. Recent work has sought to train fair models without sensitive attributes on training data. However, these methods need extensive hyper-parameter tuning to achieve good results, and hence …

abstract arxiv balance classification cs.ai cs.lg fair gender machine machine learning performance practice privacy race race and gender subgroups train training type