Graph Convolutional Neural Networks via Scattering

Graph Convolutional Neural Networks via Scattering
复制标题

DOI:
10.1016/j.acha.2019.06.003
复制
发表时间:
2018-03
期刊:
ArXiv
影响因子:
--
通讯作者:
Dongmian Zou;Gilad Lerman
Dongmian Zou;Gilad Lerman
中科院分区:
其他
文献类型:
--
作者:
Dongmian Zou;Gilad Lerman

文献摘要

相似文献

我们将散射变换推广到图上,从而在图上构造一个卷积神经网络。我们表明,在一定条件下,这样的网络产生的任何功能是近似不变的排列和稳定的信号和图形操作。数值结果表明,相关数据集上的竞争力的表现。
We generalize the scattering transform to graphs and consequently construct a convolutional neural network on graphs. We show that under certain conditions, any feature generated by such a network is approximately invariant to permutations and stable to signal and graph manipulations. Numerical results demonstrate competitive performance on relevant datasets.