BriefGPT.xyz
Dec, 2020
Sheaf 神经网络
Sheaf Neural Networks
HTML
PDF
Jakob Hansen, Thomas Gebhart
TL;DR
本文提出了一种基于sheaf Laplacian的sheaf神经网络,该网络通过泛化已有的graph convolutional networks模型中的扩散操作,提供了一种proper generalization的方法,以适用于节点间关系非恒定、非对称、不同维度的领域。研究结果表明,在节点之间关系非对称且带符号的领域,sheaf神经网络可以优于graph convolutional networks。
Abstract
We present a generalization of
graph convolutional networks
by generalizing the
diffusion operation
underlying this class of graph neural networks. These
→