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 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.
Abstract (translated)
近年来,图神经网络(GNNs)在节点分类、边预测和图表示等任务方面取得了显著进展。然而,挑战在于偏见可能不仅存在于节点属性中,而且存在于实体之间的连接中。因此,在图形神经网络学习中确保公平性成为一个关键问题。为了解决这个问题,我们提出了一个用于训练公平性感知GNN的新模型,该模型增强了反事实增强公平图神经网络框架(CAF)。我们对三个真实数据集的实验验证表明,与CAF和其他基于图的学习方法相比,我们提出的模型具有优越性。
URL
https://arxiv.org/abs/2404.06090