BriefGPT.xyz
Mar, 2021
图上自适应特征传播:超越低通滤波器
Beyond Low-Pass Filters: Adaptive Feature Propagation on Graphs
HTML
PDF
Sean Li, Dongwoo Kim, Qing Wang
TL;DR
提出了一种使用多个可学习谱滤波器的节点注意力机制的柔性图神经网络(GNN)模型,将聚合方案适应性地学习到每个图的谱域,从而更好地应对任意类型的图并在节点分类任务中取得了优越成果。
Abstract
graph neural networks
(GNNs) have been extensively studied for prediction tasks on graphs. Aspointed out by recent studies, most GNNs assume
local homophily
, i.e., strong similarities in localneighborhoods. This
→