Polarized message-passing in graph neural networks

Polarized message-passing in graph neural networks

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 neighbor...

Full description

Bibliographic Details
Main Authors: He, Tiantian, Liu, Yang, Ong, Yew-Soon, Wu, Xiaohu, Luo, Xin
Other Authors: School of Computer Science and Engineering
Format: Journal Article
Language:English
Published: 2024
Subjects:
Computer and Information Science
Graph neural networks
Message-passing graph neural networks
Online Access:https://hdl.handle.net/10356/180033

Internet

https://hdl.handle.net/10356/180033

Similar Items