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

arXiv:2311.01591v2 Announce Type: replace
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. …

abstract adversarial art arxiv communities cs.lg data decisions fair gnns graph graph neural networks impact imputation networks neural networks paper state tasks type work