BriefGPT.xyz
Jul, 2019
谱图卷积神经网络的可传递性
Transferability of Spectral Graph Convolutional Neural Networks
HTML
PDF
Ron Levie, Michael M. Bronstein, Gitta Kutyniok
TL;DR
本文重点介绍了频谱图卷积神经网络(ConvNets)并阐述了其在分析不同的图时的泛化能力,分析了滤波器的可转换性以及它们对顶点重编和大幅度图形扰动的鲁棒性,最终证明相同现象的不同图之间的滤波器可转换性。
Abstract
This paper focuses on
spectral graph convolutional neural networks
(ConvNets), where
filters
are defined as elementwise multiplication in the frequency domain of a graph. In machine learning settings where the da
→