Learning Fair Graph Neural Networks with Limited and Private Sensitive Attribute Information

Graph neural networks (GNNs) have shown great power in modeling graph structured data. However, similar to other machine learning models, GNNs may make biased predictions w.r.t protected sensitive attributes, e.g., skin color and gender. This is because the training data often contains historical bias towards sensitive attributes. In addition, we empirically show that the discrimination in GNNs can be magnified by graph structures and the message-passing mechanism of GNNs. As a result, the applications of GNNs in high-stake domains such as crime rate prediction would be largely limited. Though extensive studies of fair classification have been conducted on i.i.d data, methods to address the problem of discrimination on non-i.i.d data are rather limited. Generally, learning fair models require abundant sensitive attributes to regularize the model. However, for many graphs such as social networks, users are reluctant to share sensitive attributes. Thus, only limited sensitive attributes are available for fair GNN training in practice. Moreover, directly collecting and applying the sensitive attributes in fair model training may cause privacy issues, because the sensitive information can be leaked in data breach or attacks on the trained model. Therefore, we study a novel and crucial problem of learning fair GNNs with limited and private sensitive attribute information. In an attempt to address these problems, FairGNN is proposed to eliminate the bias of GNNs whilst maintaining high accuracy by leveraging graph structures and limited sensitive information. We further extend FairGNN to NT-FairGNN which can achieve both fairness and privacy on sensitive attributes by using limited and private sensitive attributes. Theoretical analysis and extensive experiments on real-world datasets demonstrate the effectiveness of FairGNN and NT-FairGNN in achieving fair and high-accurate classification.