Unprocessing Seven Years of Algorithmic Fairness

arXiv:2306.07261v5 Announce Type: replace
Abstract: Seven years ago, researchers proposed a postprocessing method to equalize the error rates of a model across different demographic groups. The work launched hundreds of papers purporting to improve over the postprocessing baseline. We empirically evaluate these claims through thousands of model evaluations on several tabular datasets. We find that the fairness-accuracy Pareto frontier achieved by postprocessing contains all other methods we were feasibly able to evaluate. In doing so, we address two common methodological …

abstract algorithmic fairness arxiv cs.cy cs.lg datasets error fairness papers researchers tabular through type work