Fairness of Classifiers in the Presence of Constraints between Features

ArXi:2605.00592v1 Announce Type: cross In Machine Learning, an accepted definition of fairness of a decision taken by a classifier is that it should not depend on protected features, such as gender. Unfortunately, when constraints exist between features, such dependencies can be obscured by the constraints. To avoid this problem, we propose that a decision be considered fair if it has a fair explanation.