Fair Graph Neural Network with Supervised Contrastive Regularization

arXiv:2404.06090v1 Announce Type: new
Abstract: In recent years, Graph Neural Networks (GNNs) have made significant advancements, particularly in tasks such as node classification, link prediction, and graph representation. However, challenges arise from biases that can be hidden not only in the node attributes but also in the connections between entities. Therefore, ensuring fairness in graph neural network learning has become a critical problem. To address this issue, we propose a novel model for training fairness-aware GNN, which enhances the Counterfactual …

abstract arxiv biases challenges classification cs.ai cs.lg fair gnns graph graph neural network graph neural networks graph representation hidden however link prediction network networks neural network neural networks node prediction regularization representation tasks type