ERGCN: Data enhancement-based robust graph convolutional network against adversarial attacks
Authors:
- Tao WuTWTao Wu
- Nan YangNYNan Yang
- Long ChenLCLong Chen
- Xiaokui XiaoXXXiaokui Xiao
- Xingping XianXXXingping Xian
- Jun LiuJLJun Liu
- Shaojie QiaoSQShaojie Qiao
- Canyixing CuiCCCanyixing Cui
- 31 October 2022
- journal article
- research article
- Published by Elsevier in Information Sciences
- Vol. 617, 234-253
Abstract
No abstract availableKeywords
Funding Information
- Chongqing Postdoctoral Science Foundation (cstc2021jcyj-bsh0176)
- National Natural Science Foundation of China (61802039, 62106030)
- Natural Science Foundation of Chongqing Municipality
- Chongqing Municipal Education Commission (cstc2020jcyj-msxmX0804)
- Chongqing Research Program of Basic Research and Frontier Technology (cstc2021jcyj-msxmX0530)
This publication has 28 references indexed in Scilit:
- GA-Based Q-Attack on Community DetectionIEEE Transactions on Computational Social Systems, 2019
- Safe Machine Learning and Defeating Adversarial AttacksIEEE Security & Privacy, 2019
- Real-time constrained cycle detection in large dynamic graphsProceedings of the VLDB Endowment, 2018
- Adversarial Attacks on Neural Networks for Graph Data2018
- Smooth Neighbors on Teacher Graphs for Semi-Supervised Learning2018
- DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks2016
- Collective Classification in Network DataAI Magazine, 2008
- Hierarchical structure and the prediction of missing links in networksNature, 2008
- Link-based Classification2006
- Birds of a Feather: Homophily in Social NetworksAnnual Review of Sociology, 2001