Efficient Stealthily Biased Sampling Using Sliced Wasserstein Distance

Abstract

Ensuring fairness is essential when implementing machine learning models to practical use. However, recent research has revealed that one can craft a benchmark dataset as a fake evidence of fairness from unfair models. The existing method, Stealthily Biased Sampling, solves a minimization of Wasserstein distance, which is computationally challenging when applied to large datasets. In this study, we formulate Stealthily Biased Sampling as the minimization of Sliced Wasserstein distance, demonstrating its feasibility for efficient computations.