SPMGAE: Self-purified masked graph autoencoders release robust expression power

doi:10.1016/j.neucom.2024.128631

	SPMGAE: Self-purified masked graph autoencoders release robust expression power
	Song, Shuhan 1,2; Li, Ping 1,2; Dun, Ming 1; Zhang, Yuan 1; Cao, Huawei 1,3; Ye, Xiaochun 1
	2025
发表期刊	NEUROCOMPUTING
ISSN	0925-2312
卷号	611 页码:14
摘要	To tackle the scarcity of labeled graph data, graph self-supervised learning (SSL) has branched into two paradigms: Generative methods and Contrastive methods. Inspired by MAE and BERT in computer vision (CV) and natural language processing (NLP), masked graph autoencoders (MGAEs) are gaining popularity in the generative genre. However, prevailing MGAEs are mostly designed under the assumption that the data has high homophilic score and is out of adversarial distortion. When people deliberately improve the performance on homophilic graph datasets, they ignore a critical issue that both internal heterophily and artificial attack noise are quite common in the real world. Therefore, when data itself is highly heterophilic or confronted with attacks, they merely have no defensive capability. Especially under self-supervised conditions, it is much more difficult to detect internal heterophily and resist artificial attacks. In this paper, we propose a Self-Purified Masked Graph Autoencoder (SPMGAE) to make up for the shortcomings of prevailing MGAEs in terms of robustness. SPMGAE first utilizes a self-purified module to prune raw graph data and separate perturbation information. The purified graph provides a robust graph structure for the entire pre-training process. Next, the encoding module reuses perturbation information for auxiliary training to enhance robustness, while the decoding module reconstructs the effective graph data at a finer granularity. Extensive experiments on homophilic and heterophilic datasets attacked by various attack methods demonstrate SPMGAE has a considerable robust expressive ability. Especially on small datasets with large perturbations, the improvement of defensive performance could reaches 10%-25%.
关键词	Graph neural networks Masked graph autoencoders Robustness Graph adversarial attacks
DOI	10.1016/j.neucom.2024.128631
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program[2023YFB4502305] ; Beijing Natural Science Foundation[4232036]
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:001327273600001
出版者	ELSEVIER
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/39572
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Cao, Huawei
作者单位	1.Chinese Acad Sci, Inst Comp Technol, State Key Lab Processors, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Beijing, Peoples R China 3.Zhongguancun Lab, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Song, Shuhan,Li, Ping,Dun, Ming,et al. SPMGAE: Self-purified masked graph autoencoders release robust expression power[J]. NEUROCOMPUTING,2025,611:14.
APA	Song, Shuhan,Li, Ping,Dun, Ming,Zhang, Yuan,Cao, Huawei,&Ye, Xiaochun.(2025).SPMGAE: Self-purified masked graph autoencoders release robust expression power.NEUROCOMPUTING,611,14.
MLA	Song, Shuhan,et al."SPMGAE: Self-purified masked graph autoencoders release robust expression power".NEUROCOMPUTING 611(2025):14.