Revisiting Edge Perturbation for Graph Neural Network in Graph Data Augmentation and Attack

doi:10.1109/TKDE.2025.3565306

	Revisiting Edge Perturbation for Graph Neural Network in Graph Data Augmentation and Attack
	Liu, Xin 1; Zhang, Yuxiang 1; Wu, Meng 1; Yan, Mingyu 1; He, Kun 2; Yan, Wei 1,3; Pan, Shirui 4; Ye, Xiaochun 1; Fan, Dongrui 1
	2025-07-01
发表期刊	IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
ISSN	1041-4347
卷号	37 期号:7 页码:4225-4238
摘要	Edge perturbation is a basic method to modify graph structures. It can be categorized into two veins based on their effects on the performance of graph neural networks (GNNs), i.e., graph data augmentation and attack. Surprisingly, both veins of edge perturbation methods employ the same operations, yet yield opposite effects on GNNs' accuracy. A distinct boundary between these methods in using edge perturbation has never been clearly defined. Consequently, inappropriate perturbations may lead to undesirable outcomes, necessitating precise adjustments to achieve desired effects. Therefore, questions of "why edge perturbation has a two-faced effect?" and "what makes edge perturbation flexible and effective?" still remain unanswered. In this paper, we will answer these questions by proposing a unified formulation and establishing a quantizable boundary between two categories of edge perturbation methods. Specifically, we conduct experiments to elucidate the differences and similarities between these methods and theoretically unify the workflow of these methods by casting it to one optimization problem. Then, we devise Edge Priority Detector (EPD) to generate a novel priority metric, bridging these methods up in the workflow. Experiments show that EPD can make augmentation or attack flexibly and achieve comparable or superior performance to other counterparts with less time overhead.
关键词	Perturbation methods Graph neural networks Image edge detection Data augmentation Accuracy Training Measurement Optimization Detectors World Wide Web Edge perturbation graph neural network graph data augmentation graph data attack
DOI	10.1109/TKDE.2025.3565306
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program[2023YFB4502305] ; National Natural Science Foundation of China[62202451] ; National Natural Science Foundation of China[62302477] ; CAS Project for Young Scientists in Basic Research[YSBR-029] ; CAS Project for Youth Innovation Promotion Association
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Information Systems ; Engineering, Electrical & Electronic
WOS记录号	WOS:001504151700027
出版者	IEEE COMPUTER SOC
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/42352
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Yan, Mingyu
作者单位	1.Chinese Acad Sci, Inst Comp Technol, SKLP, Beijing 100086, Peoples R China 2.Renmin Univ China, Beijing 100872, Peoples R China 3.Zhongguancun Lab, Beijing 100086, Peoples R China 4.Griffith Univ, Brisbane, Qld 4111, Australia
推荐引用方式 GB/T 7714	Liu, Xin,Zhang, Yuxiang,Wu, Meng,et al. Revisiting Edge Perturbation for Graph Neural Network in Graph Data Augmentation and Attack[J]. IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING,2025,37(7):4225-4238.
APA	Liu, Xin.,Zhang, Yuxiang.,Wu, Meng.,Yan, Mingyu.,He, Kun.,...&Fan, Dongrui.(2025).Revisiting Edge Perturbation for Graph Neural Network in Graph Data Augmentation and Attack.IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING,37(7),4225-4238.
MLA	Liu, Xin,et al."Revisiting Edge Perturbation for Graph Neural Network in Graph Data Augmentation and Attack".IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 37.7(2025):4225-4238.