Multi-Fair Pareto Boosting

Fairness-aware machine learning for multiple protected at-tributes (referred to as multi-fairness hereafter) is receiving increasing attention as traditional single-protected attribute approaches cannot en-sure fairness w.r.t. other protected attributes. Existing methods, how-ever, still ignore the fact that datasets in this domain are often imbalanced, leading to unfair decisions towards the minority class. Thus, solutions are needed that achieve multi-fairness,accurate predictive performance in overall, and balanced performance across the different classes.To this end, we introduce a new fairness notion,Multi-Max Mistreatment(MMM), which measures unfairness while considering both (multi-attribute) protected group and class membership of instances. To learn an MMM-fair classifier, we propose a multi-objective problem formulation. We solve the problem using a boosting approach that in-training,incorporates multi-fairness treatment in the distribution update and post-training, finds multiple Pareto-optimal solutions; then uses pseudo-weight based decision making to select optimal solution(s) among accurate, balanced, and multi-attribute fair solutions