Knowledge Commons of Institute of Automation,CAS
Robust Graph Neural Networks Against Adversarial Attacks via Jointly Adversarial Training | |
Tian Hu1,2; Ye Bowei3; Zheng Xiaolong1,2; Zhang Xingwei1,2; Wu Dash Desheng4 | |
2021-04 | |
会议名称 | 3rd IFAC Workshop on Cyber-Physical & Human Systems |
会议日期 | 2020-12-3 |
会议地点 | 上海 |
摘要 | Graph neural networks (GNNs) are powerful tools for analyzing graph-structured data. However, recent studies have shown that GNNs are vulnerable to small but intentional perturbations of input features and graph structures in the node classification task. Existing researches focus on enhancing the robustness of GNNs for a single type of perturbation such as graph structure perturbation or node feature perturbation. An ideal graph neural networks model should be able to resist the two kinds of perturbations. For this purpose, we propose a new adversarial training method for graph-structured data named Graph Jointly Adversarial |
收录类别 | EI |
语种 | 英语 |
七大方向——子方向分类 | 社会计算 |
国重实验室规划方向分类 | 社会系统建模与计算 |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/52319 |
专题 | 多模态人工智能系统全国重点实验室_互联网大数据与信息安全 |
通讯作者 | Zheng Xiaolong |
作者单位 | 1.中国科学院自动化研究所 2.中国科学院大学人工智能学院 3.University of Illinois in Urbana-Champaign 4.中国科学院大学 |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Tian Hu,Ye Bowei,Zheng Xiaolong,et al. Robust Graph Neural Networks Against Adversarial Attacks via Jointly Adversarial Training[C],2021. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Tianhu-CPHS-2021.pdf(443KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论