BriefGPT.xyz
Nov, 2021
通过曲率理解图形上的压缩和瓶颈
Understanding over-squashing and bottlenecks on graphs via curvature
HTML
PDF
Jake Topping, Francesco Di Giovanni, Benjamin Paul Chamberlain, Xiaowen Dong, Michael M. Bronstein
TL;DR
本文研究图神经网络中信息传递中的over-squashing问题, 通过引入基于曲率的重连方法以减轻该问题，同时探究其根源为图中负曲率边所导致的瓶颈现象。
Abstract
Most
graph neural networks
(GNNs) use the
message passing paradigm
, in which node features are propagated on the input graph. Recent works pointed to the distortion of information flowing from distant nodes as a
→