arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2005.10203cs.LGcs.CRcs.SIstat.ML
收藏

鲁棒图神经网络的图结构学习

Graph Structure Learning for Robust Graph Neural Networks

Michigan State University(密歇根州立大学);The Pennsylvania State University(宾夕法尼亚州立大学)

Wei Jin, Yao Ma, Xiaorui Liu, Xianfeng Tang, Suhang Wang, Jiliang Tang

摘要:

图神经网络(GNN)是图的表示学习的强大工具。然而,最近的研究表明,GNN容易受到精心设计的扰动,称为对抗攻击。对抗攻击可以很容易地欺骗GNN对下游任务进行预测。对抗攻击的脆弱性已经引起了人们对在安全关键型应用中应用GNN的越来越多的关注。因此,研究鲁棒的防御对抗攻击的算法具有重要意义。防御对抗攻击的一个自然想法是清理扰动图。很明显,真实世界的图共享一些内在属性。例如,许多现实世界的图是低秩和稀疏的,并且两个相邻节点的特征往往是相似的。事实上,我们发现对抗攻击很可能违反这些图形属性。因此,在本文中,我们探索这些属性,以抵御图上的对抗攻击。特别地,我们提出了一个通用框架Pro-GNN,它可以从这些属性指导的扰动图中联合学习结构图和鲁棒的图神经网络模型。在真实世界的图形上进行的大量实验表明,与最先进的防御方法相比,即使图形受到严重干扰,所提出的框架也可以实现更好的性能。我们将Pro-GNN的实现发布到DeepRobust存储库中,用于对抗攻击和防御(脚注:https://github.com/DSE-MSU/DeepRobust)。重现我们的结果的具体实验设置可以在https://github.com/ChandlerBang/Pro-GNN中找到。

英文摘要:

Graph Neural Networks (GNNs) are powerful tools in representation learning for graphs. However, recent studies show that GNNs are vulnerable to carefully-crafted perturbations, called adversarial attacks. Adversarial attacks can easily fool GNNs in making predictions for downstream tasks. The vulnerability to adversarial attacks has raised increasing concerns for applying GNNs in safety-critical applications. Therefore, developing robust algorithms to defend adversarial attacks is of great significance. A natural idea to defend adversarial attacks is to clean the perturbed graph. It is evident that real-world graphs share some intrinsic properties. For example, many real-world graphs are low-rank and sparse, and the features of two adjacent nodes tend to be similar. In fact, we find that adversarial attacks are likely to violate these graph properties. Therefore, in this paper, we explore these properties to defend adversarial attacks on graphs. In particular, we propose a general framework Pro-GNN, which can jointly learn a structural graph and a robust graph neural network model from the perturbed graph guided by these properties. Extensive experiments on real-world graphs demonstrate that the proposed framework achieves significantly better performance compared with the state-of-the-art defense methods, even when the graph is heavily perturbed. We release the implementation of Pro-GNN to our DeepRobust repository for adversarial attacks and defenses (footnote: https://github.com/DSE-MSU/DeepRobust). The specific experimental settings to reproduce our results can be found in https://github.com/ChandlerBang/Pro-GNN.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑