Graph Neural Networks (GNNs) are able to achieve high classification accuracy on many large real world datasets, but provide no rigorous notion of predictive uncertainty. We leverage recent advances in conformal prediction to construct prediction sets for node classification in inductive learning scenarios, and verify the efficacy of our approach across standard benchmark datasets using popular GNN models. The code is available at \href{https://github.com/jase-clarkson/graph_cp}{this link}.

翻译：神经网络(Neural Networks)能够实现许多大型真实世界数据集的高分类精确度,但不能提供预测不确定性的严格概念。 我们利用近期在一致性预测方面的进展来构建用于感化学习情景节点分类的预测数据集,并利用广受欢迎的GNN模型来验证我们跨标准基准数据集的方法的有效性。 该代码可在以下网站查阅:https://github.com/jase-clarkson/graph_cp ⁇ _thy continution}