中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
SAQE: Complex Logical Query Answering via Semantic-Aware Representation Learning

文献类型：期刊论文

作者Cao, Zongsheng2,3,4; Xu, Qianqian5; Yang, Zhiyong6; He, Yuan7; Cao, Xiaochun8; Huang, Qingming1,5,9
刊名IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
出版日期2025-11-01
卷号37期号:11页码:6651-6665
关键词Cognition Knowledge graphs Representation learning Semantics Optimization Logic Accuracy Data mining Training Artificial intelligence Knowledge graph logic query answering semantic-aware learning hierarchical reasoning optimization
ISSN号1041-4347
DOI10.1109/TKDE.2025.3603877
英文摘要Performing complex First-Order Logic (FOL) queries on knowledge graphs is crucial for advancing knowledge reasoning. Knowledge graphs encapsulate rich semantic interactions among entities, encompassing both explicit structural knowledge represented by triples (e1,r,e2) and implicit relational knowledge through multi-hop paths (e1(r1)->& ctdot;e3 & ctdot;(r2)-> e2). Traditional models often focus solely on either triple-level or path-level knowledge, overlooking the benefits of integrating both to enhance logic query answering. This oversight leads to suboptimal representation learning and inefficient query reasoning. To overcome these challenges, we introduce a new Semantic-Aware representation learning model for Query-answering Embeddings (SAQE). Specifically, SAQE employs a joint learning approach that integrates triple-level and path-level knowledge semantics and captures both explicit and implicit contextual nuances within the knowledge graph, yielding more accurate and contextually relevant representations. To efficiently handle the large combinatorial search spaces in FOL reasoning, we propose a novel hierarchical reasoning optimization strategy by a multi-hop tree thus optimizing subqueries rooted at variable nodes in a divide-and-conquer manner. Theoretical analysis confirms that SAQE effectively supports various types of FOL reasoning and enhances generalizations for query answering. Extensive experiments demonstrate that our model achieves state-of-the-art performance across several established datasets.
资助项目National Key R#x0026;D Program of China[2018AAA0102000] ; National Natural Science Foundation of China[62236008] ; National Natural Science Foundation of China[62441232] ; National Natural Science Foundation of China[U21B2038] ; National Natural Science Foundation of China[U23B2051] ; National Natural Science Foundation of China[62122075] ; Youth Innovation Promotion Association CAS ; Strategic Priority Research Program of the Chinese Academy of Sciences[XDB0680201]
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:001589873500025
出版者IEEE COMPUTER SOC
源URL[http://119.78.100.204/handle/2XEOYT63/41660]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Xu, Qianqian; Huang, Qingming
作者单位1.Peng Cheng Lab, Shenzhen 518055, Peoples R China
2.Univ Chinese Acad Sci, Sch Cyber Secur, Beijing 101408, Peoples R China
3.Chinese Acad Sci, Inst Informat Engn, State Key Lab Informat Secur SKLOIS, Beijing 100045, Peoples R China
4.Shanghai AI Lab, Shanghai 200231, Peoples R China
5.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China
6.Univ Chinese Acad Sci, Sch Comp Sci & Technol, Beijing 100049, Peoples R China
7.Alibaba Grp, Secur Dept, Hangzhou 311121, Peoples R China
8.Sun Yat Sen Univ, Sch Cyber Sci & Technol, Shenzhen Campus, Shenzhen 518107, Peoples R China
9.Univ Chinese Acad Sci, Sch Comp Sci & Technol, Key Lab Big Data Min & Knowledge Management BDKM, Beijing 101408, Peoples R China
推荐引用方式
GB/T 7714		 Cao, Zongsheng,Xu, Qianqian,Yang, Zhiyong,et al. SAQE: Complex Logical Query Answering via Semantic-Aware Representation Learning[J]. IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING,2025,37(11):6651-6665.
APA Cao, Zongsheng,Xu, Qianqian,Yang, Zhiyong,He, Yuan,Cao, Xiaochun,&Huang, Qingming.(2025).SAQE: Complex Logical Query Answering via Semantic-Aware Representation Learning.IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING,37(11),6651-6665.
MLA Cao, Zongsheng,et al."SAQE: Complex Logical Query Answering via Semantic-Aware Representation Learning".IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 37.11(2025):6651-6665.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。