BriefGPT.xyz
Nov, 2023
Riemannian图神经网络中的过度压缩
Over-Squashing in Riemannian Graph Neural Networks
HTML
PDF
Julia Balla
TL;DR
本研究探索了通过图神经网络的嵌入空间来减轻过度压缩现象，特别关注于将双曲型图神经网络推广到可变曲率的黎曼流形，以使嵌入空间的几何与图的拓扑相符，通过提供敏感性的界限结果，实现在具有负曲率的图中减轻过度压缩的有希望的理论和实证结果。
Abstract
Most
graph neural networks
(GNNs) are prone to the phenomenon of
over-squashing
in which node features become insensitive to information from distant nodes in the graph. Recent works have shown that the topology
→