BIG: A Practical Framework for Balancing the Conflict Between Group and Individual Fairness in Graph Neural Networks

Graph neural networks (GNNs) nowadays play a vital role in many high-stakes applications due to their powerful data representation capabilities. In recent years, the issue of fairness discrimination in GNNs has gained significant attention. Existing methods endow different concepts of fairness in GNNs, mainly focusing on group and individual fairness, and give corresponding solution frameworks. However, these existing methods usually only consider optimizing one kind of fairness and claim that group and individual fairness are conflicting and cannot be handled together. Such an approach has limitations and lacks practicality for real-world application scenarios. In this paper, we propose a GNN-based framework for resolving the conflict between group and individual fairness, namely BIG (Balancing Individual and Group fairness). First, we expound on the view that group and individual fairness do not conflict and define a novel notion named balanced fairness and the corresponding evaluation metric. Second, we propose the framework structure and algorithm principle of BIG. Finally, we evaluate the effectiveness of BIG on three real-world datasets. The experimental results show that BIG balances group fairness and individual fairness in GNNs well while ensuring the accuracy of the node classification tasks.