Are Fair Learning To Rank Models Really Fair? An Analysis Using Inferred Gender

Abstract

Fair Learning To Rank (LTR) frameworks require demographic information; however, that information is often unavailable. Inference algorithms may infer the missing demographic information to supply to the fair LTR model. In this study, we analyze the effect of using a trained fair LTR model with uncertain demographic inferences. We show that inferred data results in varying levels of fairness and utility depending on inference accuracy. Specifically, less accurate inferred data adversely affects the rankings’ fairness, while more accurate inferred data creates fairer rankings. Therefore, we recommend that a careful evaluation of demographic inference algorithms before use is critical.