Real-world classification datasets often contain label bias, where observed labels differ systematically from the true labels at different rates for different demographic groups. Machine learning models trained on such datasets may then exhibit disparities in predictive performance across these groups. In this work, we characterize the problem of learning fair classification models with respect to the underlying ground truth labels when given only label biased data. We focus on the particular fairness definition of group sufficiency, i.e. equal calibration of risk scores across protected groups. We theoretically show that enforcing fairness with respect to label biased data necessarily results in group miscalibration with respect to the true labels. We then propose a regularizer which minimizes an upper bound on the sufficiency gap by penalizing a conditional mutual information term. Across experiments on eight tabular, image, and text datasets with both synthetic and real label noise, we find that our method reduces the sufficiency gap by up to 7.2% with no significant decrease in overall accuracy.

Standard learning approaches are designed to perform well on average for the data distribution available at training time. Developing learning approaches that are not overly sensitive to the training distribution is central to research on domain- or out-of-distribution generalization, robust optimization and fairness. In this work we focus on links between research on domain generalization and algorithmic fairness -- where performance under a distinct but related test distributions is studied -- and show how the two fields can be mutually beneficial. While domain generalization methods typically rely on knowledge of disjoint "domains" or "environments", "sensitive" label information indicating which demographic groups are at risk of discrimination is often used in the fairness literature. Drawing inspiration from recent fairness approaches that improve worst-case performance without knowledge of sensitive groups, we propose a novel domain generalization method that handles the more realistic scenario where environment partitions are not provided. We then show theoretically and empirically how different partitioning schemes can lead to increased or decreased generalization performance, enabling us to outperform Invariant Risk Minimization with handcrafted environments in multiple cases. We also show how a re-interpretation of IRMv1 allows us for the first time to directly optimize a common fairness criterion, group-sufficiency, and thereby improve performance on a fair prediction task.

We clarify what fairness guarantees we can and cannot expect to follow from unconstrained machine learning. Specifically, we characterize when unconstrained learning on its own implies group calibration, that is, the outcome variable is conditionally independent of group membership given the score. We show that under reasonable conditions, the deviation from satisfying group calibration is upper bounded by the excess risk of the learned score relative to the Bayes optimal score function. A lower bound confirms the optimality of our upper bound. Moreover, we prove that as the excess risk of the learned score decreases, it strongly violates separation and independence, two other standard fairness criteria. Our results show that group calibration is the fairness criterion that unconstrained learning implicitly favors. On the one hand, this means that calibration is often satisfied on its own without the need for active intervention, albeit at the cost of violating other criteria that are at odds with calibration. On the other hand, it suggests that we should be satisfied with calibration as a fairness criterion only if we are at ease with the use of unconstrained machine learning in a given application.