In this paper, we present Polarized message-passing (PMP), a novel paradigm to revolutionize the design of message-passing graph neural networks (GNNs). In contrast to existing methods, PMP captures the power of node-node similarity and dissimilarity to acquire dual sources of messages from neighbors. The messages are then coalesced to enable GNNs to learn expressive representations from sparse but strongly correlated neighbors. Three novel GNNs based on the PMP paradigm, namely PMP graph convolutional network (PMP-GCN), PMP graph attention network (PMP-GAT), and PMP graph PageRank network (PMP-GPN) are proposed to perform various downstream tasks. Theoretical analysis is also conducted to verify the high expressiveness of the proposed PMP-based GNNs. In addition, an empirical study of five learning tasks based on 12 real-world datasets is conducted to validate the performances of PMP-GCN, PMP-GAT, and PMP-GPN. The proposed PMP-GCN, PMP-GAT, and PMP-GPN outperform numerous strong message-passing GNNs across all five learning tasks, demonstrating the effectiveness of the proposed PMP paradigm.

中文翻译：

---

图神经网络中的极化消息传递

在本文中，我们提出了极化消息传递（PMP），这是一种彻底改变消息传递图神经网络（GNN）设计的新颖范式。与现有方法相比，PMP 利用节点间相似性和不相似性的力量来获取来自邻居的双重消息源。然后将这些消息合并起来，使 GNN 能够从稀疏但强相关的邻居中学习表达表示。提出了三种基于 PMP 范式的新型 GNN，即 PMP 图卷积网络（PMP-GCN）、PMP 图注意力网络（PMP-GAT）和 PMP 图 PageRank 网络（PMP-GPN）来执行各种下游任务。还进行了理论分析来验证所提出的基于 PMP 的 GNN 的高表达能力。此外，基于 12 个真实数据集对 5 个学习任务进行了实证研究，以验证 PMP-GCN、PMP-GAT 和 PMP-GPN 的性能。所提出的 PMP-GCN、PMP-GAT 和 PMP-GPN 在所有五个学习任务中都优于众多强大的消息传递 GNN，证明了所提出的 PMP 范式的有效性。