BriefGPT.xyz
Jun, 2020
图境神经网络与图神经网络的可迁移性
Graphon Neural Networks and the Transferability of Graph Neural Networks
HTML
PDF
Luana Ruiz, Luiz F. O. Chamon, Alejandro Ribeiro
TL;DR
本文介绍了图神经网络(GNN)的转移性以及与该特性相关的图卷积和限制对象图形神经网络(Graphon NNs),证明了一个GNN和其极限图形的输出之间的差异,该差异随着节点数量的增加而消失,如果图卷积滤波器在图谱域中是带限制的,则该结果确立了GNN的可辨别性和可传输性之间的权衡。
Abstract
graph neural networks
(GNNs) rely on
graph convolutions
to extract local features from network data. These
graph convolutions
combine info
→