<ul><li>Graph Neural Networks (GNNs) have become the leading approach for addressing graph analytical problems in various real-world scenarios.</li><li>GNNs may produce biased predictions against certain demographic subgroups due to node attributes and neighbors surrounding a node.</li><li>Current research on GNN fairness often uses oversimplified fairness evaluation metrics, resulting in misleading impressions of fairness.</li><li>ComFairGNN is a novel framework designed to mitigate community-level bias in GNNs by employing a learnable coreset-based debiasing function.</li></ul>

ComFairGNN: Community Fair Graph Neural Network

Discover more