BriefGPT.xyz
Jun, 2020
图神经网络中过度平滑问题的注记
A Note on Over-Smoothing for Graph Neural Networks
HTML
PDF
Chen Cai, Yusu Wang
TL;DR
本研究分析图神经网络在层数增加时出现的过度平滑现象,通过使用增广归一化拉普拉斯矩阵的频谱确定权重矩阵的条件,来说明当嵌入的狄利克雷能量收敛于零时,图嵌入的区分能力会丧失。通过使用狄利克雷能量来衡量嵌入的表达能力,可以得到比已有研究更简单的证明,并可处理更多的非线性问题。
Abstract
graph neural networks
(GNNs) have achieved a lot of success on graph-structured data. However, it is observed that the performance of
graph neural networks
does not improve as the number of layers increases. This
→