GAHE: Geometry-Aware Embedding for Hyper-Relational Knowledge Graph Representation

doi:10.1145/3733602

	GAHE: Geometry-Aware Embedding for Hyper-Relational Knowledge Graph Representation
	Cao, Zongsheng 1; Xu, Qianqian 2; Yang, Zhiyong 3; He, Yuan 4; Cao, Xiaochun 5; Huang, Qingming 3
	2025-07-01
发表期刊	ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS
ISSN	1551-6857
卷号	21 期号:7 页码:26
摘要	Knowledge graphs have proven highly effective for learning representations of entities and relations, with hyper-relational knowledge graphs (HKGs) gaining increased attention due to their enhanced representation capabilities. Each fact in an HKG consists of a main triple supplemented by attribute-value qualifiers that provide additional contextual information. Due to the complexity of hyper-relations, HKGs typically contain complex geometric structures, such as hierarchical, ring, and chain structures, often mixed together. However, previous work mainly embeds HKGs into Euclidean space, limiting their ability to capture these complex geometric structures simultaneously. To address this challenge, we propose a novel model called geometryaware hyper-relational embedding (GAHE). Specifically, GAHE adopts a multi-curvature geometry-aware approach by modeling HKGs in Euclidean space (zero curvature), hyperbolic space (negative curvature), and hyperspherical space (positive curvature) in a unified framework. In this way, it can integrate spaceinvariant and space-specific features to accurately capture the diverse structures in HKGs. In addition, GAHE introduces a module termed hyper-relational subspace learning, which allocates multiple sub-relations for each hyper-relation. It enables the exploitation of abundant latent semantic interactions and facilitates the exploration of fine-grained semantics between attribute-value pairs and hyper-relations across multiple subspaces. Furthermore, we provide theoretical guarantees that GAHE is fully expressive and capable of modeling a wide range of semantic patterns for hyper-relations. Empirical evaluations demonstrate that GAHE achieves state-of-the-art results on both hyper-relational and binary-relational benchmarks.
关键词	Knowledge Graph Hyper-relational Learning Multicurvature Spaces Geometry Aware
DOI	10.1145/3733602
收录类别	SCI
语种	英语
WOS研究方向	Computer Science
WOS类目	Computer Science, Information Systems ; Computer Science, Software Engineering ; Computer Science, Theory & Methods
WOS记录号	WOS:001540889700002
出版者	ASSOC COMPUTING MACHINERY
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/42001
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, Zongsheng
作者单位	1.Chinese Acad Sci, State Key Lab Informat Secur SKLOIS, Inst Informat Engn, Beijing, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing, Peoples R China 3.Univ Chinese Acad Sci, Sch Comp Sci & Technol, Beijing, Peoples R China 4.Alibaba Grp, Secur Dept, Beijing, Peoples R China 5.Sun Yat Sen Univ, Sch Cyber Sci & Technol, Shenzhen Campus, Shenzhen, Peoples R China
推荐引用方式 GB/T 7714	Cao, Zongsheng,Xu, Qianqian,Yang, Zhiyong,et al. GAHE: Geometry-Aware Embedding for Hyper-Relational Knowledge Graph Representation[J]. ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS,2025,21(7):26.
APA	Cao, Zongsheng,Xu, Qianqian,Yang, Zhiyong,He, Yuan,Cao, Xiaochun,&Huang, Qingming.(2025).GAHE: Geometry-Aware Embedding for Hyper-Relational Knowledge Graph Representation.ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS,21(7),26.
MLA	Cao, Zongsheng,et al."GAHE: Geometry-Aware Embedding for Hyper-Relational Knowledge Graph Representation".ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS 21.7(2025):26.