Egalitarian Machine Learning

Ethical concerns about this widespread practice have given rise to the young field of fair machine learning and a number of fairness measures--mathematically precise definitions of fairness that purport to determine whether a given prediction-based decision system is fair. Following Reuben Binns, I take “fairness” in this context to be a placeholder for a variety of normative egalitarian considerations. I explore a few fairness measures to suss out their egalitarian roots and evaluate them, both as formalizations of egalitarian ideas and as assertions of what fairness demands of predictive systems. I pay special attention to a recent and promising fairness measure, counterfactual fairness, which holds that a prediction about an individual is fair if it is the same in the actual world and any counterfactual world where the individual belongs to a different demographic group.

Author: Clinton Castro