.png){kind=icon}
.png){kind=icon}
Return
Framelet message passing
.png){kind=icon}
PRE
AI
DOI：10.1016/j.acha.2025.101773.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Graph neural networks have achieved champions in wide applications. Neural message passing is a typical key module for feature propagation by aggregating neighboring features. In this work, we propose a new message passing based on multiscale framelet transforms, called Framelet Message Passing. Different from traditional spatial methods, it integrates framelet representation of neighbor nodes from multiple hops away in node message update. We also propose a continuous message passing using neural ODE solvers. Both discrete and continuous cases can provably mitigate oversmoothing and achieve superior performance. Numerical experiments on real graph datasets show that the continuous version of the framelet message passing significantly outperforms existing methods when learning heterogeneous graphs and achieves state-of-the-art performance on classic node classification tasks with low computational costs.
Keywords:
graph neural networks
message passing
framelet transforms
oversmoothing
neural ODE
Journal
IF:
3.2
Papers:
95
Citations:
3.9K