BriefGPT.xyz
Jun, 2019
通过重连对图卷积网络进行攻击
Attacking Graph Convolutional Networks via Rewiring
HTML
PDF
Yao Ma, Suhang Wang, Lingfei Wu, Jiliang Tang
TL;DR
本文提出了一种针对图神经网络的对抗攻击方法，通过图重连的操作，使用强化学习生成对于目标模型影响较小的扰动，并在真实图数据集上进行实验及分析，证明该方法的有效性。
Abstract
graph neural networks
(GNNs) have boosted the performance of many graph related tasks such as node classification and graph classification. Recent researches show that
graph neural networks
are vulnerable to
→