Causal Fairness under Unobserved Confounding: A Neural Sensitivity Framework

arXiv:2311.18460v2 Announce Type: replace
Abstract: Fairness for machine learning predictions is widely required in practice for legal, ethical, and societal reasons. Existing work typically focuses on settings without unobserved confounding, even though unobserved confounding can lead to severe violations of causal fairness and, thus, unfair predictions. In this work, we analyze the sensitivity of causal fairness to unobserved confounding. Our contributions are three-fold. First, we derive bounds for causal fairness metrics under different sources of unobserved confounding. This enables practitioners …

abstract analyze arxiv confounding cs.ai cs.cy cs.lg ethical fairness framework legal machine machine learning practice predictions sensitivity stat.me type work