Node classification across networks via category-level domain adaptive network embedding

doi:10.1007/s10115-023-01942-2

	Node classification across networks via category-level domain adaptive network embedding
	Shi, Boshen 1,2; Wang, Yongqing 1; Shao, Jiangli 1,2; Shen, Huawei 1; Li, Yangyang 3,4; Cheng, Xueqi 1
	2023-07-30
发表期刊	KNOWLEDGE AND INFORMATION SYSTEMS
ISSN	0219-1377
页码	24
摘要	To improve the performance of classifying nodes on unlabeled or scarcely-labeled networks, the task of node classification across networks is proposed for transferring knowledge from similar networks with rich labels. As data distribution shift exists across networks, domain adaptive network embedding is proposed to overcome such challenge by learning network-invariant and discriminative node embeddings, in which domain adaptation technique is applied to network embedding for reducing domain discrepancy. However, existing works merely discuss category-level domain discrepancy which is crucial to better adaptation and classification. In this paper, we propose category-level domain adaptive network embedding. The key idea is minimizing intra-class domain discrepancy and maximizing inter-class domain discrepancy between source and target networks simultaneously. To further enhance classification performance on target network, we reduce embedding variation inside each class and enlarge it between different classes. Graph attention network is adopted for learning network embeddings. In addition, a novel pseudo-labeling strategy for target network is developed to better compute category-level information. Theoretical analysis guarantees the effectiveness of our model. Furthermore, extensive experiments on real-world datasets show that our model achieves the state-of-art performance, in particular, outperforming existing domain adaptive network embedding models by up to 32%.
关键词	Node classification across networks Graph neural networks Domain adaptation Transfer learning
DOI	10.1007/s10115-023-01942-2
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[U21B2046] ; China Postdoctoral Science Foundation[2022M713206]
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Information Systems
WOS记录号	WOS:001039402200001
出版者	SPRINGER LONDON LTD
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/21288
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Shi, Boshen; Wang, Yongqing
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Data Intelligence Syst Res Ctr, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Comp Sci & Technol, Beijing 100049, Peoples R China 3.CAEIT, Natl Engn Res Ctr Risk Percept & Prevent NEL RPP, Beijing 100041, Peoples R China 4.Acad Cyber, Beijing 100085, Peoples R China
推荐引用方式 GB/T 7714	Shi, Boshen,Wang, Yongqing,Shao, Jiangli,et al. Node classification across networks via category-level domain adaptive network embedding[J]. KNOWLEDGE AND INFORMATION SYSTEMS,2023:24.
APA	Shi, Boshen,Wang, Yongqing,Shao, Jiangli,Shen, Huawei,Li, Yangyang,&Cheng, Xueqi.(2023).Node classification across networks via category-level domain adaptive network embedding.KNOWLEDGE AND INFORMATION SYSTEMS,24.
MLA	Shi, Boshen,et al."Node classification across networks via category-level domain adaptive network embedding".KNOWLEDGE AND INFORMATION SYSTEMS (2023):24.