We study fairness in collaborative-filtering recommender systems, which are sensitive to discrimination that exists in historical data. Biased data can lead collaborative-filtering methods to make unfair predictions for users from minority groups. We identify the insufficiency of existing fairness metrics and propose four new metrics that address different forms of unfairness. These fairness metrics can be optimized by adding fairness terms to the learning objective. Experiments on synthetic and real data show that our new metrics can better measure fairness than the baseline, and that the fairness objectives effectively help reduce unfairness.

Algorithmic decisions about individuals require predictions that are not only accurate but also fair with respect to sensitive attributes such as gender and race. Causal notions of fairness align with legal requirements, yet many methods assume access to detailed knowledge of the underlying causal graph, which is a demanding assumption in practice. We propose a learning framework that achieves interventional fairness by leveraging a causal graph over \textit{clusters of variables}, which is substantially easier to estimate than a variable-level graph. With possible \textit{adjustment cluster sets} identified from such a cluster causal graph, our framework trains a prediction model by reducing the worst-case discrepancy between interventional distributions across these sets. To this end, we develop a computationally efficient barycenter kernel maximum mean discrepancy (MMD) that scales favorably with the number of sensitive attribute values. Extensive experiments show that our framework strikes a better balance between fairness and accuracy than existing approaches, highlighting its effectiveness under limited causal graph knowledge.

We address the problem of performing regression while ensuring demographic parity, even without access to sensitive attributes during inference. We present a general-purpose post-processing algorithm that, using accurate estimates of the regression function and a sensitive attribute predictor, generates predictions that meet the demographic parity constraint. Our method involves discretization and stochastic minimization of a smooth convex function.

We call this distinction thediscrimination risk. We prove that a higher discrimination risk can amplify the unfairness of a machine learning model applied totheimputed data.

Fair machine learning.Generally, fair machine learning methods fall into three categories: preprocessing, in-processing, and post-processing [44, 7]. In this paper, we focus on in-processing methods thatmodify learning algorithms toremovediscrimination during thetraining process. All of those works are for indistribution fairness, and we investigate out-of-distribution fairness in this paper. Weuse LAFTR [42],anadversarial learning method that showsadvanced performance onfairness [47],tolearn a fair model in the source domain and adapt it to the target domain. We also test CFair[72] in our experiments.

While the main paper only contains proof sketches or intuitions, all complete proofsarereportedinAppendixA.