提出首个图神经网络不确定性量化方法，用集合预测提升可靠性。
Credal Graph Neural Networks
- 用可信集输出替代传统概率，实现图神经网络的可信学习
- 在异质图分布外场景下，不确定性估计更可靠且性能领先
- 适合需要高可信度决策的图学习应用，如金融风控
不确定性量化对部署可靠的图神经网络（GNNs）至关重要，现有方法主要依赖贝叶斯推断或集成。本文首次提出可信图神经网络（CGNNs），将可信学习扩展至图领域，训练GNN输出以可信集形式存在的集合值预测。针对GNN消息传递的独特性，我们设计了一种互补的可信学习方法，利用层间信息传播的不同方面。我们在分布外条件下的节点分类任务中评估该方法，分析表明图同质性假设对不确定性估计效果起关键作用。大量实验表明，CGNNs在异质图分布偏移下能提供更可靠的表征认知不确定性，并达到当前最优性能。
原文摘要 · Abstract (English)
Uncertainty quantification is essential for deploying reliable Graph Neural Networks (GNNs), where existing approaches primarily rely on Bayesian inference or ensembles. In this paper, we introduce the first credal graph neural networks (CGNNs), which extend credal learning to the graph domain by training GNNs to output set-valued predictions in the form of credal sets. To account for the distinctive nature of message passing in GNNs, we develop a complementary approach to credal learning that leverages different aspects of layer-wise information propagation. We assess our approach on uncertainty quantification in node classification under out-of-distribution conditions. Our analysis highlights the critical role of the graph homophily assumption in shaping the effectiveness of uncertainty estimates. Extensive experiments demonstrate that CGNNs deliver more reliable representations of epistemic uncertainty and achieve state-of-the-art performance under distributional shift on heterophilic graphs.
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。