What is Fair? Exploring Pareto-Efficiency for Fairness Constrained Classifiers
This addresses fairness in machine learning for societal applications, offering an incremental improvement over strict fairness constraints.
The paper tackles the problem of fairness constraints causing uneven performance degradation across subgroups by proposing Pareto-Efficient Fairness (PEF), which identifies optimal points on the Pareto curve to maximize subgroup accuracies, empirically showing improved performance on UCI datasets.
The potential for learned models to amplify existing societal biases has been broadly recognized. Fairness-aware classifier constraints, which apply equality metrics of performance across subgroups defined on sensitive attributes such as race and gender, seek to rectify inequity but can yield non-uniform degradation in performance for skewed datasets. In certain domains, imbalanced degradation of performance can yield another form of unintentional bias. In the spirit of constructing fairness-aware algorithms as societal imperative, we explore an alternative: Pareto-Efficient Fairness (PEF). Theoretically, we prove that PEF identifies the operating point on the Pareto curve of subgroup performances closest to the fairness hyperplane, maximizing multiple subgroup accuracy. Empirically we demonstrate that PEF outperforms by achieving Pareto levels in accuracy for all subgroups compared to strict fairness constraints in several UCI datasets.