核图卷积神经网络

Oct, 2017

Kernel Graph Convolutional Neural Networks

Giannis Nikolentzos, Polykarpos Meladianos, Antoine Jean-Pierre Tixier, Konstantinos Skianis, Michalis Vazirgiannis

TL;DR本文旨在利用图形核函数解决图形数据处理问题，通过选取合适的滤波器、池化层以及前馈神经网络进行特征学习，最终在十个基准数据集的七个中达到了优异的表现。

Abstract

graph kernels have been successfully applied to many graph classification problems. Typically, a kernel is first designed, and then an svm classifier is trained based on the features defined implicitly by this ke