2020/02/07 by Steffen Grünewälder, Grünewälder, Steffen, Azadeh Khaleghi +1 · 1 citation
Computer Science · Mathematics · #Adversarial Robustness in Machine Learning #Explainable Artificial Intelligence (XAI) #Generative Adversarial Networks and Image Synthesis #cs.LG #math.ST #stat.ML #stat.TH
paper · pdf · doi:10.48550/arxiv.2002.02901
arxiv created 2020/11/19 · arxiv updated 2020/11/23
We investigate the problem of algorithmic fairness in the case where sensitive and non-sensitive features are available and one aims to generate new, `oblivious', features that closely approximate the non-sensitive features, and are only minimally dependent on the sensitive ones. We study this question in the context of kernel methods. We analyze a relaxed version of the Maximum Mean Discrepancy criterion which does not guarantee full independence but makes the optimization problem tractable. We derive a closed-form solution for this relaxed optimization problem and complement the result with a study of the dependencies between the newly generated features and the sensitive ones. Our key ingredient for generating such oblivious features is a Hilbert-space-valued conditional expectation, which needs to be estimated from data. We propose a plug-in approach and demonstrate how the estimation errors can be controlled. While our techniques help reduce the bias, we would like to point out that no post-processing of any dataset could possibly serve as an alternative to well-designed experiments.