Polarized message-passing in graph neural networks

Tiantian He, Yang Liu, Yew-Soon Ong, Xiaohu Wu, Xin Luo

Abstract: Highlights•A novel paradigm PMP is proposed to enable GNNs to learn more expressive representations.•Novel GNN architectures, namely PMP-GCN, PMP-GAT, and PMP-GPN are constructed for various downstream tasks.•The expressiveness of the PMP-based GNNs is theoretically guaranteed.