Better Fair than Sorry: Adversarial Missing Data Imputation for Fair GNNs

This paper addresses the problem of learning fair Graph Neural Networks (GNNs) under missing protected attributes. GNNs have achieved state-of-the-art results in many relevant tasks where decisions might disproportionately impact specific communities. However, existing work on fair GNNs assumes that either protected attributes are fully-observed or that the missing data imputation is fair. In practice, biases in the imputation will be propagated to the model outcomes, leading them to overestimate the fairness of their predictions. We address this challenge by proposing Better Fair than Sorry (BFtS), a fair missing data imputation model for protected attributes used by fair GNNs. The key design principle behind BFtS is that imputations should approximate the worst-case scenario for the fair GNN -- i.e. when optimizing fairness is the hardest. We implement this idea using a 3-player adversarial scheme where two adversaries collaborate against the fair GNN. Experiments using synthetic and real datasets show that BFtS often achieves a better fairness $\times$ accuracy trade-off than existing alternatives.