Search for: All records

As learning-to-rank models are increasingly deployed for decision-making in areas with profound life implications, the FairML community has been developing fair learning-to-rank (LTR) models. These models rely on the availability of sensitive demographic features such as race or sex. However, in practice, regulatory obstacles and privacy concerns protect this data from collection and use. As a result, practitioners may either need to promote fairness despite the absence of these features or turn to demographic inference tools to attempt to infer them. Given that these tools are fallible, this paper aims to further understand how errors in demographic inference impact the fairness performance of popular fair LTR strategies. In which cases would it be better to keep such demographic attributes hidden from models versus infer them? We examine a spectrum of fair LTR strategies ranging from fair LTR with and without demographic features hidden versus inferred to fairness-unaware LTR followed by fair re-ranking. We conduct a controlled empirical investigation modeling different levels of inference errors by systematically perturbing the inferred sensitive attribute. We also perform three case studies with real-world datasets and popular open-source inference methods. Our findings reveal that as inference noise grows, LTR-based methods that incorporate fairness considerations into the learning process may increase bias. In contrast, fair re-ranking strategies are more robust to inference errors. All source code, data, and experimental artifacts of our experimental study are available here: https://github.com/sewen007/hoiltr.git 

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.