Fair Graph Neural Network with Supervised Contrastive Regularization
It addresses fairness issues in GNNs for tasks like node classification, which is important for mitigating biases in graph-based learning, though it appears incremental as it builds on the CAF framework.
The paper tackled fairness in Graph Neural Networks (GNNs) by proposing a model that integrates Supervised Contrastive Loss and Environmental Loss to enhance accuracy and fairness, demonstrating superiority over existing methods like CAF on three real datasets.
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 Augmented Fair Graph Neural Network Framework (CAF). Our approach integrates Supervised Contrastive Loss and Environmental Loss to enhance both accuracy and fairness. Experimental validation on three real datasets demonstrates the superiority of our proposed model over CAF and several other existing graph-based learning methods.