Improving Fairness in Graph Neural Networks via Mitigating Sensitive Attribute Leakage
Improving Fairness in Graph Neural Networks via Mitigating Sensitive Attribute Leakage
复制标题
DOI：
10.1145/3534678.3539404
复制
发表时间：
2022-06
期刊：
影响因子：
--
通讯作者：
Yu Wang;Yuying Zhao;Yushun Dong;Huiyuan Chen;Jundong Li;Tyler Derr
中科院分区：
文献类型：
--
作者：
Yu Wang;Yuying Zhao;Yushun Dong;Huiyuan Chen;Jundong Li;Tyler Derr
图神经网络（Graph Neural Networks，GNNs）在学习图上的节点表示方面展现出了强大的能力。然而，它们可能会从训练数据中继承历史偏见，导致预测中出现歧视性偏差。尽管一些研究已经开发出了公平的图神经网络，但其中大多数直接从非图领域借用公平表示学习技术，而没有考虑到图神经网络中特征传播可能导致的敏感属性泄露问题。然而，我们通过实验观察到，特征传播可能会改变先前无害的非敏感特征与敏感特征之间的相关性。这可以被视为敏感信息的泄露，它可能会进一步加剧预测中的歧视。因此，我们根据特征相关性设计了两种特征掩码策略，以强调在减轻歧视时考虑特征传播和相关性变化的重要性。受我们分析的启发，我们提出了公平视角图神经网络（Fair View Graph Neural Network，FairVGNN），通过在考虑特征传播后的相关性变化的情况下自动识别和掩码与敏感特征相关的特征来生成特征的公平视角。给定学习到的公平视角，我们自适应地限制编码器的权重，以避免使用与敏感相关的特征。在真实数据集上的实验表明，FairVGNN在模型效用和公平性之间取得了更好的平衡。
Graph Neural Networks (GNNs) have shown great power in learning node representations on graphs. However, they may inherit historical prejudices from training data, leading to discriminatory bias in predictions. Although some work has developed fair GNNs, most of them directly borrow fair representation learning techniques from non-graph domains without considering the potential problem of sensitive attribute leakage caused by feature propagation in GNNs. However, we empirically observe that feature propagation could vary the correlation of previously innocuous non-sensitive features to the sensitive ones. This can be viewed as a leakage of sensitive information which could further exacerbate discrimination in predictions. Thus, we design two feature masking strategies according to feature correlations to highlight the importance of considering feature propagation and correlation variation in alleviating discrimination. Motivated by our analysis, we propose Fair View Graph Neural Network (FairVGNN) to generate fair views of features by automatically identifying and masking sensitive-correlated features considering correlation variation after feature propagation. Given the learned fair views, we adaptively clamp weights of the encoder to avoid using sensitive-related features. Experiments on real-world datasets demonstrate that FairVGNN enjoys a better trade-off between model utility and fairness.