Contrastive Multi-Modal Knowledge Graph Representation Learning

doi:10.1109/TKDE.2022.3220625

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

	Contrastive Multi-Modal Knowledge Graph Representation Learning
	Fang, Quan 2; Zhang, Xiaowei 1; Hu, Jun 2; Wu, Xian 3; Xu, Changsheng 2,4
刊名	IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
	2023-09-01
卷号	35 期号:9 页码:8983-8996
关键词	Knowledge graph multimedia graph neural network contrastive learning
ISSN号	1041-4347
DOI	10.1109/TKDE.2022.3220625
通讯作者	Xu, Changsheng(csxu@nlpr.ia.ac.cn)
英文摘要	Representation learning of knowledge graphs (KGs) aims to embed both entities and relations as vectors in a continuous low-dimensional space, which has facilitated various applications such as link prediction and entity retrieval. Most existing KG embedding methods focus on modeling the structured fact triples independently and ignore the multi-type relations among triples as well as the variety of data types (e.g., texts and images) associated with entities in KGs, and thus fail to capture the complex and multi-modal information that is inherently inside the entity-relation triples. In this paper, we propose a novel approach for knowledge graph embedding named Contrastive Multi-modal Graph Neural Network (CMGNN), which can encapsulate comprehensive features from multi-modal content descriptions of entities and high-order connectivity structures. Specifically, CMGNN first learns entity embeddings from multi-modal content and then contrasts encodings from multi-relational local neighbors and high-order connectivities to obtain latent representations of entities and relations simultaneously. Experimental results demonstrate that CMGNN can effectively model the multi-modalities and multi-type structures in KGs, and significantly outperforms existing state-of-the-art methods on benchmark datasets for the tasks of link prediction and entity classification.
资助项目	National Natural Science Foundation of China[62072456] ; National Natural Science Foundation of China[62036012] ; National Natural Science Foundation of China[62106262] ; Open Research Projects of Zhejiang Lab[2021KE0AB05]
WOS关键词	NETWORK
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	IEEE COMPUTER SOC
WOS记录号	WOS:001045704800021
资助机构	National Natural Science Foundation of China ; Open Research Projects of Zhejiang Lab
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/53969]
专题	多模态人工智能系统全国重点实验室
通讯作者	Xu, Changsheng
作者单位	1.Zhengzhou Univ, Zhengzhou 450001, Peoples R China 2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 3.Tencent Med AI Lab, Beijing 100080, Peoples R China 4.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Fang, Quan,Zhang, Xiaowei,Hu, Jun,et al. Contrastive Multi-Modal Knowledge Graph Representation Learning[J]. IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING,2023,35(9):8983-8996.
APA	Fang, Quan,Zhang, Xiaowei,Hu, Jun,Wu, Xian,&Xu, Changsheng.(2023).Contrastive Multi-Modal Knowledge Graph Representation Learning.IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING,35(9),8983-8996.
MLA	Fang, Quan,et al."Contrastive Multi-Modal Knowledge Graph Representation Learning".IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 35.9(2023):8983-8996.