论文标题
1-wl表现力是（几乎）您需要的
1-WL Expressiveness Is (Almost) All You Need
论文作者
论文摘要
已经表明，传递神经网络（MPNN）的消息是一个流行的用于图形结构化数据的神经网络家族，最多像一阶Weisfeiler-Leman（1-WL）图同构测试一样表现力，这激发了更多表现力架构的开发。在这项工作中，我们分析有限的表现力实际上是标准图数据集中MPNN和其他基于WL的模型的限制因素。有趣的是，我们发现WL的表现力足以在大多数数据集中识别几乎所有图表。此外，我们发现分类精度上限通常接近100 \％。此外，我们发现可以将基于WL的简单神经网络和几个MPNN安装在几个数据集中。总而言之，我们得出的结论是，WL/MPNN的性能不受其在实践中的表现力的限制。
It has been shown that a message passing neural networks (MPNNs), a popular family of neural networks for graph-structured data, are at most as expressive as the first-order Weisfeiler-Leman (1-WL) graph isomorphism test, which has motivated the development of more expressive architectures. In this work, we analyze if the limited expressiveness is actually a limiting factor for MPNNs and other WL-based models in standard graph datasets. Interestingly, we find that the expressiveness of WL is sufficient to identify almost all graphs in most datasets. Moreover, we find that the classification accuracy upper bounds are often close to 100\%. Furthermore, we find that simple WL-based neural networks and several MPNNs can be fitted to several datasets. In sum, we conclude that the performance of WL/MPNNs is not limited by their expressiveness in practice.
