Graph generative model evaluation necessitates understanding differences between graphs on the distributional level. This entails being able to harness salient attributes of graphs in an efficient manner. Curvature constitutes one such property of graphs, and has recently started to prove useful in characterising graphs. Its expressive properties, stability, and practical utility in model evaluation remain largely unexplored, however. We combine graph curvature descriptors with cutting-edge methods from topological data analysis to obtain robust, expressive descriptors for evaluating graph generative models.

翻译：图生成模型的评估需要理解图在分布层面上的差异，这要求能够高效地利用图的显著属性。曲率作为图的属性之一，近年来在表征图方面开始展现出其有效性，但其表达特性、稳定性以及在模型评估中的实际效用仍很大程度上未被探索。我们将图曲率描述符与拓扑数据分析的前沿方法相结合，以获得稳健且富有表达力的描述符，用于评估图生成模型。