提出CUQ-GNN，用委员会机制更灵活地量化图数据不确定性。
CUQ-GNN: Committee-based Graph Uncertainty Quantification using Posterior Networks
- 结合GNN与后验网络，通过委员会机制估计节点不确定性
- 在多个基准上表现优于GPN，生成更符合实际的置信度
- 适合对不确定性敏感的应用，如医疗诊断、金融风控
本文研究了在图数据上定义有意义预测不确定性的领域特性影响。先前提出的图后验网络（GPN）利用归一化流（NFs）独立估计每个节点的类别密度，并将其转换为狄利克雷伪计数，再通过个性化页面排序算法在图上传播。GPN架构基于三个关于不确定性估计性质的公理，但实践中这些公理常不成立。为此，我们提出一类基于委员会的图不确定性量化图神经网络（CUQ-GNN），将标准图神经网络与基于归一化流的后验网络不确定性估计相结合，更灵活地适应特定领域的不确定性需求。我们在常见节点分类基准上对比了CUQ-GNN与GPN及其他不确定性量化方法，结果表明其能有效生成有用且可靠的不确定性估计。
原文摘要 · Abstract (English)
In this work, we study the influence of domain-specific characteristics when defining a meaningful notion of predictive uncertainty on graph data. Previously, the so-called Graph Posterior Network (GPN) model has been proposed to quantify uncertainty in node classification tasks. Given a graph, it uses Normalizing Flows (NFs) to estimate class densities for each node independently and converts those densities into Dirichlet pseudo-counts, which are then dispersed through the graph using the personalized Page-Rank algorithm. The architecture of GPNs is motivated by a set of three axioms on the properties of its uncertainty estimates. We show that those axioms are not always satisfied in practice and therefore propose the family of Committe-based Uncertainty Quantification Graph Neural Networks (CUQ-GNNs), which combine standard Graph Neural Networks with the NF-based uncertainty estimation of Posterior Networks (PostNets). This approach adapts more flexibly to domain-specific demands on the properties of uncertainty estimates. We compare CUQ-GNN against GPN and other uncertainty quantification approaches on common node classification benchmarks and show that it is effective at producing useful uncertainty estimates.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。