Graph Neural Networks (GNNs) are able to achieve high classification accuracy on many important real world datasets, but provide no rigorous notion of predictive uncertainty. Quantifying the confidence of GNN models is difficult due to the dependence between datapoints induced by the graph structure. We leverage recent advances in conformal prediction to construct prediction sets for node classification in inductive learning scenarios. We do this by taking an existing approach for conformal classification that relies on \textit{exchangeable} data and modifying it by appropriately weighting the conformal scores to reflect the network structure. We show through experiments on standard benchmark datasets using popular GNN models that our approach provides tighter and better calibrated prediction sets than a naive application of conformal prediction.

翻译：图神经网络（GNN）能够在许多重要的真实世界数据集上实现高分类准确率，但无法提供预测不确定性的严格度量。由于图结构所导致的数据点依赖性，量化GNN模型的置信度十分困难。我们利用共形预测的最新进展，在归纳学习场景中为节点分类构建预测集。具体而言，我们采用一种依赖\textit{可交换}数据的现有共形分类方法，并通过适当加权共形得分以反映网络结构对其进行改进。在标准基准数据集上使用主流GNN模型的实验表明，与共形预测的朴素应用相比，我们的方法能提供更紧凑且校准更优的预测集。