节点分类图神经网络中的差异、不平等与准确率权衡
Disparity, Inequality, and Accuracy Tradeoffs in Graph Neural Networks for Node Classification
AI总结：
针对GNN节点分类中的群体偏见问题，提出PFR-AX与PostProcess两种模型无关干预，并通过多数据集实验评估公平性与准确率权衡。
摘要：
图神经网络（GNN）正越来越多地用于关键的人类应用，以预测属性图中的节点标签。它们聚合节点邻居特征以实现准确分类的能力，也可能加剧数据中现有的偏见，或对受保护人口群体成员引入新的偏见。因此，必须量化GNN可能如何产生偏见，以及其有害影响在多大程度上可以被缓解。为此，我们提出两种新的、与GNN无关的干预措施，即：(i) PFR-AX，它降低受保护组与非受保护组中节点之间的可分离性；以及(ii) PostProcess，它基于黑盒策略更新模型预测，以最小化不同人口群体之间错误率的差异。通过在四个数据集上进行的大量实验，我们从算法公平性—准确率权衡的角度阐述了我们的方法（及三个变体）的有效性，并在三种最先进的GNN模型上，将我们的结果与三种强基线干预措施进行基准比较。结果表明，没有任何单一干预措施能提供普遍最优的权衡，但PFR-AX和PostProcess提供了细粒度控制，并在正确预测受保护组节点的正向结果时提升了模型置信度。
英文摘要：
Graph neural networks (GNNs) are increasingly used in critical human applications for predicting node labels in attributed graphs. Their ability to aggregate features from nodes' neighbors for accurate classification also has the capacity to exacerbate existing biases in data or to introduce new ones towards members from protected demographic groups. Thus, it is imperative to quantify how GNNs may be biased and to what extent their harmful effects may be mitigated. To this end, we propose two new GNN-agnostic interventions namely, (i) PFR-AX which decreases the separability between nodes in protected and non-protected groups, and (ii) PostProcess which updates model predictions based on a blackbox policy to minimize differences between error rates across demographic groups. Through a large set of experiments on four datasets, we frame the efficacies of our approaches (and three variants) in terms of their algorithmic fairness-accuracy tradeoff and benchmark our results against three strong baseline interventions on three state-of-the-art GNN models. Our results show that no single intervention offers a universally optimal tradeoff, but PFR-AX and PostProcess provide granular control and improve model confidence when correctly predicting positive outcomes for nodes in protected groups.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
