Message Passing Neural Networks (MPNNs) are a common type of Graph Neural Network (GNN), in which each node's representation is computed recursively by aggregating representations (messages) from its immediate neighbors akin to a star-shaped pattern. MPNNs are appealing for being efficient and scalable, how-ever their expressiveness is upper-bounded by the 1st-order Weisfeiler-Lehman isomorphism test (1-WL). In response, prior works propose highly expressive models at the cost of scalability and sometimes generalization performance. Our work stands between these two regimes: we introduce a general framework to uplift any MPNN to be more expressive, with limited scalability overhead and greatly improved practical performance. We achieve this by extending local aggregation in MPNNs from star patterns to general subgraph patterns (e.g.,k-egonets):in our framework, each node representation is computed as the encoding of a surrounding induced subgraph rather than encoding of immediate neighbors only (i.e. a star). We choose the subgraph encoder to be a GNN (mainly MPNNs, considering scalability) to design a general framework that serves as a wrapper to up-lift any GNN. We call our proposed method GNN-AK(GNN As Kernel), as the framework resembles a convolutional neural network by replacing the kernel with GNNs. Theoretically, we show that our framework is strictly more powerful than 1&2-WL, and is not less powerful than 3-WL. We also design subgraph sampling strategies which greatly reduce memory footprint and improve speed while maintaining performance. Our method sets new state-of-the-art performance by large margins for several well-known graph ML tasks; specifically, 0.08 MAE on ZINC,74.79% and 86.887% accuracy on CIFAR10 and PATTERN respectively.

翻译：信息传递神经网络 (MPNNN) 是平面神经网络 (GNN) 的一种常见类型。 在其中,每个节点的表达方式都是通过将近邻的表达方式(消息)归结为类似于恒星形状的模式来反复计算。 MPNN 要求高效且可缩放, 它们的表达性无论如何受一阶Weisfeiler-Lehman变形测试( 1- WL) 的上层限制 。 作为回应, 先前的著作提出了高清晰度的模型, 成本是可缩放, 有时是通用的。 我们的工作处于这两个制度之间: 我们引入了一个总框架, 提升任何MPNNNN( 缩放) 以更清晰的表达方式, 将本地的运行方式从恒星模式扩大到一般子模式( e.g.k-godents): 在我们的框架中,每个节点的表达方式被我们周围的子框架比直接邻居( i.e. cal) 和近邻的编码更清楚。 我们选择一个子目录框架, GNNNND( 以G) 格式向G-ral-ral 格式显示我们的一般设计, 而以G-NNF-ral 格式向G-ral 要求。