A critique of the use of counterfactuals in ethical machine learning
Artist: Kirill Maksimchuk
A critique of the use of counterfactuals in ethical machine learning
Atoosa Kasirzadeh & Andrew Smart (Google)
Virtual NeurIPS 2020 Workshop on Algorithmic Fairness through the Lens of Causality and Interpretability. December 12 2020.
In this paper, we argue that even though counterfactuals play an essential part in some causal inferences, their use for questions of algorithmic fairness and social explanations can create more problems than they resolve. Our result is a set of tenets about using counterfactuals for fairness and explanations in machine learning.
Click here for more information.