当前位置: X-MOL 学术Inform. Sci. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Robust node embedding against graph structural perturbations
Information Sciences Pub Date : 2021-03-04 , DOI: 10.1016/j.ins.2021.02.046
Zhendong Zhao , Xiaojun Chen , Dakui Wang , Yuexin Xuan , Gang Xiong

Despite achieving superior performance for many graph-related tasks, recent works have shown that Graph Neural Networks (GNNs) are vulnerable to adversarial attacks on graph structures. In particular, by adding or removing a small number of carefully selected edges in a graph, an adversary can maliciously manipulate a GNNs-based classifier. The vulnerability to adversarial attacks poses numerous concerns for employing GNNs in real-world applications. Previously research aims to overcome the negative impact from adversarial edges with graph-based regularization of some heuristic properties. However, the real-world graph data is far more intricate, and these defense mechanisms do not fully utilize comprehensive semantic information of graph data. In this work, we present a novel defense method, Holistic Semantic Constraint Graph Neural Network (HSC-GNN), which approaches the joint modeling of the node features, labels, and the graph structure to mitigate the effects of malicious perturbations. Extensive experimental evaluation under various graph datasets demonstrates that our approach results in more robust node embedding and better performance than existing models.



中文翻译:

强大的节点嵌入功能,可抵抗图结构扰动

尽管在许多与图相关的任务上均取得了卓越的性能,但最近的研究表明,图神经网络(GNN)容易受到图结构的对抗性攻击。尤其是,通过在图中添加或删除少量精心选择的边缘,对手可能会恶意操纵基于GNN的分类器。对抗攻击的漏洞引起了在现实世界中应用GNN的众多问题。以前的研究旨在通过对某些启发式属性进行基于图的正则化来克服对抗性边缘带来的负面影响。但是,现实世界中的图形数据要复杂得多,并且这些防御机制不能充分利用图形数据的全面语义信息。在这项工作中,我们提出了一个新的防御方法,^ h olistic小号emantic Ç onstraint ģ拍摄和Ñ eural Ñ etwork(HSC-GNN),其接近所述节点的联合建模功能,标签和图形结构,以减轻恶意扰动的影响。在各种图形数据集下进行的广泛实验评估表明,与现有模型相比,我们的方法可实现更强大的节点嵌入和更好的性能。

更新日期:2021-03-29
down
wechat
bug