提出新方法，让图模型能准确评估预测不确定性。
GraphPPD: Posterior Predictive Modelling for Graph-Level Inference
- 基于现有GNN的图嵌入，构建可自适应学习的后验预测分布框架。
- 在多个基准数据集上验证了其在图级任务中量化不确定性的有效性。
- 适合需要可信预测的图学习场景，如生物医药分析、社交网络推理。
准确建模和量化预测不确定性在深度学习中至关重要，它使模型在数据模糊时能做出更安全的决策，并帮助用户理解模型对其预测的信心。近年来，图神经网络（GNNs）研究热度持续上升，已有众多技术致力于捕捉其预测中的不确定性。然而，大多数方法仅针对节点或边级别的任务设计，无法直接应用于图级别学习问题。本文提出一种新颖的变分建模框架，用于图级别学习中的后验预测分布（Posterior Predictive Distribution, PPD），实现不确定性感知的预测。该框架基于某一现有GNN生成的图级嵌入，能够以数据自适应方式学习PPD。在多个基准数据集上的实验结果表明，该方法在图级别任务中具有显著有效性。
原文摘要 · Abstract (English)
Accurate modelling and quantification of predictive uncertainty is crucial in deep learning since it allows a model to make safer decisions when the data is ambiguous and facilitates the users' understanding of the model's confidence in its predictions. Along with the tremendously increasing research focus on \emph{graph neural networks} (GNNs) in recent years, there have been numerous techniques which strive to capture the uncertainty in their predictions. However, most of these approaches are specifically designed for node or link-level tasks and cannot be directly applied to graph-level learning problems. In this paper, we propose a novel variational modelling framework for the \emph{posterior predictive distribution}~(PPD) to obtain uncertainty-aware prediction in graph-level learning tasks. Based on a graph-level embedding derived from one of the existing GNNs, our framework can learn the PPD in a data-adaptive fashion. Experimental results on several benchmark datasets exhibit the effectiveness of our approach.
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。