Abstract: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.
Abstract:Across various sectors such as healthcare, criminal justice, national security, finance, and technology, large-scale machine learning (ML) and artificial intelligence (AI) systems are being deployed to make critical data-driven decisions. Many have asked if we can and should trust these ML systems to be making these decisions. Two critical components are prerequisites for trust in ML systems: interpretability, or the ability to understand why the ML system makes the decisions it does, and fairness, which ensures that ML systems do not exhibit bias against certain individuals or groups. Both interpretability and fairness are important and have separately received abundant attention in the ML literature, but so far, there have been very few methods developed to directly interpret models with regard to their fairness. In this paper, we focus on arguably the most popular type of ML interpretation: feature importance scores. Inspired by the use of decision trees in knowledge distillation, we propose to leverage trees as interpretable surrogates for complex black-box ML models. Specifically, we develop a novel fair feature importance score for trees that can be used to interpret how each feature contributes to fairness or bias in trees, tree-based ensembles, or tree-based surrogates of any complex ML system. Like the popular mean decrease in impurity for trees, our Fair Feature Importance Score is defined based on the mean decrease (or increase) in group bias. Through simulations as well as real examples on benchmark fairness datasets, we demonstrate that our Fair Feature Importance Score offers valid interpretations for both tree-based ensembles and tree-based surrogates of other ML systems.