Say No to the Discrimination: Learning Fair Graph Neural Networks with Limited Sensitive Attribute Information

Abstract

Graph neural networks (GNNs) have shown great power in modeling graph structured data. However, similar to other machine learning models, GNNs may make predictions biased on protected sensitive attributes, e.g., skin color and gender. Because machine learning algorithms including GNNs are trained to reflect the distribution of the training data which often contains historical bias towards sensitive attributes. In addition, the discrimination in GNNs can be magnified by graph structures and the message-passing mechanism. As a result, the applications of GNNs in sensitive 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. Furthermore, the practical scenario of sparse annotations in sensitive attributes is rarely considered in existing works. Therefore, we study the novel and important problem of learning fair GNNs with limited sensitive attribute information. FairGNN is proposed to eliminate the bias of GNNs whilst maintaining high node classification accuracy by leveraging graph structures and limited sensitive information. Our theoretical analysis shows that FairGNN can ensure the fairness of GNNs under mild conditions given limited nodes with known sensitive attributes. Extensive experiments on real-world datasets also demonstrate the effectiveness of FairGNN in debiasing and keeping high accuracy.

References in corpus (12)

• Equality of Opportunity in Supervised Learning
• Deep Convolutional Networks on Graph-Structured Data
• Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks
• Graph Convolutional Matrix Completion
• Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning
• Data Decisions and Theoretical Implications when Adversarially Learning Fair Representations
• On Fairness and Calibration
• Transferring Robustness for Graph Neural Network Against Poisoning Attacks
• Flexibly Fair Representation Learning by Disentanglement
• Unifying Graph Convolutional Neural Networks and Label Propagation
• Compositional Fairness Constraints for Graph Embeddings
• Node Injection Attacks on Graphs via Reinforcement Learning

Cited by in corpus (1)

• EDITS: Modeling and Mitigating Data Bias for Graph Neural Networks