Adversarial Heterogeneous Graph Neural Network for Robust Recommendation

doi:10.1109/TCSS.2023.3268683

CORC > 自动化研究所 > 中国科学院自动化研究所 > 多模态人工智能系统全国重点实验室

	Adversarial Heterogeneous Graph Neural Network for Robust Recommendation
	Sang, Lei 4; Xu, Min 1; Qian, Shengsheng 2; Wu, Xindong 3
刊名	IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS
	2023-05-16
页码	12
关键词	Perturbation methods Motion pictures Training Graph neural networks Robustness Semantics Predictive models Adversarial training (AT) graph neural network (GNN) heterogeneous graph recommendation
ISSN号	2329-924X
DOI	10.1109/TCSS.2023.3268683
通讯作者	Xu, Min(Min.Xu@uts.edu.au)
英文摘要	Recommendation systems play a vital role in identifying the hidden interactions between users and items in online social networks. Recently, graph neural networks (GNNs) have exhibited significant performance gains by modeling the information propagation process in graph-structured data for a recommendation. However, existing GNN-based methods do not have broad applicability to heterogeneous graphs that integrate auxiliary data with diverse types. Moreover, graph structures are susceptible to noise and even unnoticed malicious perturbations, as perturbations from connected nodes can create cumulative effects on a target node in the graph. To enhance the robustness and generalization of GNN-based recommendations, we propose a new optimization model named Adversarial Heterogeneous Graph Neural Network for RECommendation (AHGNNRec). First, AHGNNRec learns user and item embeddings by exploring the distinct contributions of various types of interactions between users and items using a hierarchical heterogeneous graph neural network (HGNN). Second, to produce more robust embeddings for recommendations, we employ the adversarial training (AT) method to optimize the HGNN layers. AT is a min-max optimization training process where the generated adversarial fake nodes from normal nodes with intentional perturbations try to maximally deteriorate the recommendation performance. Following this, we learn about these adversarial user or item nodes by minimizing the impact of an additional regularization term for the recommendation. The experimental outcomes on two real-world benchmark datasets demonstrate the effectiveness of AHGNNRec.
资助项目	National Natural Science Foundation of China[62206002] ; Anhui Provincial Natural Science Foundation[2208085QF195] ; Anhui Provincial Natural Science Foundation[2208085QF199] ; Australia Research Council (ARC) Linkage Projects[LP210100129] ; Australian Research Council[LP210100129]
WOS关键词	SHILLING ATTACKS ; SYSTEMS
WOS研究方向	Computer Science
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:001004788000001
资助机构	National Natural Science Foundation of China ; Anhui Provincial Natural Science Foundation ; Australia Research Council (ARC) Linkage Projects ; Australian Research Council
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/53468]
专题	多模态人工智能系统全国重点实验室
通讯作者	Xu, Min
作者单位	1.Univ Technol Sydney, Fac Engn & Informat Technol, Sydney, NSW 2007, Australia 2.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China 3.Hefei Univ Technol, Key Lab Knowledge Engn Big Data, Minist Educ China, Hefei 230601, Anhui, Peoples R China 4.Anhui Univ, Sch Comp Sci & Technol, Hefei 230601, Anhui, Peoples R China
推荐引用方式 GB/T 7714	Sang, Lei,Xu, Min,Qian, Shengsheng,et al. Adversarial Heterogeneous Graph Neural Network for Robust Recommendation[J]. IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS,2023:12.
APA	Sang, Lei,Xu, Min,Qian, Shengsheng,&Wu, Xindong.(2023).Adversarial Heterogeneous Graph Neural Network for Robust Recommendation.IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS,12.
MLA	Sang, Lei,et al."Adversarial Heterogeneous Graph Neural Network for Robust Recommendation".IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS (2023):12.