中文标题#
通过反事实去偏改善图神经网络的公平性
英文标题#
Improving Fairness in Graph Neural Networks via Counterfactual Debiasing
中文摘要#
图神经网络（GNNs）在建模图结构数据方面已经取得了成功。 然而，与其他机器学习模型类似，GNNs 在基于种族和性别等属性的预测中可能会表现出偏差。 此外，GNNs 中的偏差可能由于图结构和消息传递机制而加剧。 最近的前沿方法通过从输入或表示中过滤掉敏感信息来减轻偏差，例如边删除或特征掩码。 然而，我们认为这些策略可能会无意中消除非敏感特征，导致预测准确性和公平性之间的平衡受损。 为了解决这个挑战，我们提出了一种新的方法，利用反事实数据增强来减轻偏差。 该方法涉及在消息传递之前使用反事实创建多样化的邻域，从而从增强的图中学习无偏的节点表示。 随后，使用对抗性鉴别器通过传统 GNN 分类器来减少预测中的偏差。 我们提出的技术 Fair-ICD 在适度条件下确保了 GNN 的公平性。 在标准数据集上使用三种 GNN 主干进行的实验表明，Fair-ICD 显著提高了公平性指标，同时保持了高预测性能。
英文摘要#
Graph Neural Networks (GNNs) have been successful in modeling graph-structured data. However, similar to other machine learning models, GNNs can exhibit bias in predictions based on attributes like race and gender. Moreover, bias in GNNs can be exacerbated by the graph structure and message-passing mechanisms. Recent cutting-edge methods propose mitigating bias by filtering out sensitive information from input or representations, like edge dropping or feature masking. Yet, we argue that such strategies may unintentionally eliminate non-sensitive features, leading to a compromised balance between predictive accuracy and fairness. To tackle this challenge, we present a novel approach utilizing counterfactual data augmentation for bias mitigation. This method involves creating diverse neighborhoods using counterfactuals before message passing, facilitating unbiased node representations learning from the augmented graph. Subsequently, an adversarial discriminator is employed to diminish bias in predictions by conventional GNN classifiers. Our proposed technique, Fair-ICD, ensures the fairness of GNNs under moderate conditions. Experiments on standard datasets using three GNN backbones demonstrate that Fair-ICD notably enhances fairness metrics while preserving high predictive performance.
文章页面#
PDF 获取#
抖音扫码查看更多精彩内容