no code implementations • 19 Jan 2024 • Aoqi Zuo, Yiqing Li, Susan Wei, Mingming Gong
To address this limitation, this paper proposes a framework for achieving causal fairness based on the notion of interventions when the true causal graph is partially known.
no code implementations • 27 May 2022 • Aoqi Zuo, Susan Wei, Tongliang Liu, Bo Han, Kun Zhang, Mingming Gong
Interestingly, we find that counterfactual fairness can be achieved as if the true causal graph were fully known, when specific background knowledge is provided: the sensitive attributes do not have ancestors in the causal graph.