借助 BREC 数据集更好地评估 GNN 表达能力【英文版】

英文标题：Towards Better Evaluation of GNN Expressiveness with BREC Dataset中文摘要：研究了图神经网络的理论表达能力，提出了一种新的表达能力数据集 BREC，并通过对 16 种高于 1-WL 表达能力模型在 BREC 数据集上的测试对其进行了比较。英文摘要：Research on the theoretical expressiveness of Graph Neural Networks (GNNs)has developed rapidly, and many methods have been proposed to enhance theexpressiveness. However, most methods do not have a uniform expressivenessmeasure except for a few that strictly follow the $k$-dimensionalWeisfeiler-Lehman ($k$-WL) test hierarchy. Their theo