BriefGPT.xyz
Dec, 2023
自环悖论：自环对图神经网络的影响研究
The Self-Loop Paradox: Investigating the Impact of Self-Loops on Graph Neural Networks
HTML
PDF
Moritz Lampert, Ingo Scholtes
TL;DR
图神经网络中的自环与信息的回流存在自环悖论，这可以在特定的图神经网络结构中通过解析方法进行验证，并在合成节点分类任务和23个实际图中进行实验验证。
Abstract
Many
graph neural networks
(GNNs) add
self-loops
to a graph to include feature information about a node itself at each layer. However, if the GNN consists of more than one layer, this information can return to it
→