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. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 人工智能与机器学习
SLAN: Similarity-aware aggregation network for embedding out-of-knowledge-graph entities

文献类型：期刊论文

作者Li, Mingda1,2; Sun, Zhengya1,2; Zhang, Wensheng1,2
刊名NEUROCOMPUTING
出版日期2022-06-28
卷号491页码:186-196
ISSN号0925-2312
关键词Knowledge graph embedding Out-of-knowledge-graph entities Knowledge graph completion Similarity search
DOI10.1016/j.neucom.2022.03.063
通讯作者Sun, Zhengya(zhengya.sun@ia.ac.cn)
英文摘要Knowledge graph embedding acts as a pivotal role in predicting the missing information in knowledge graphs (KGs). Due to the evolving nature of real-world KGs, one requires the ability to make predictions for newly emerging entities besides those already observed at training time. Current studies have made great efforts to develop a neighborhood aggregator and embed out-of-knowledge-graph (OOKG) entities inductively, with less focus on exploiting the similarity between the existing and newly emerging enti-ties. Attaching importance to such similarity helps facilitate semantic transfer. In this work, we propose a similarity-aware aggregation network for embedding out-of-knowledge-graph entities. Motivated by the fact that similar entities are likely to occur in common graph context, we skillfully design a similarity-aware function, which measures the distance of each entity pair based on the contextual gap. Moreover, we aggregate the neighborhood surrounding the target entity and its similarity information by query-specific attention weights, which are optimized during the learning process. Extensive experi-ments on knowledge graph completion task show that our method achieves substantial improvements over baselines.(c) 2022 Elsevier B.V. All rights reserved.
资助项目National Key Research and Development Program of China[2018AAA0102100] ; National Natural Science Foundation of China[61876183] ; National Natural Science Foundation of China[61961160707] ; National Natural Science Foundation of China[61976212]
WOS研究方向Computer Science
语种英语
出版者ELSEVIER
WOS记录号WOS:000788143600016
资助机构National Key Research and Development Program of China ; National Natural Science Foundation of China
源URL[http://ir.ia.ac.cn/handle/173211/48390]  
专题精密感知与控制研究中心_人工智能与机器学习
通讯作者Sun, Zhengya
作者单位1.Chinese Acad Sci, Res Ctr Precis Sensing & Control, Inst Automat, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci UCAS, Beijing 100049, Peoples R China
推荐引用方式
GB/T 7714		 Li, Mingda,Sun, Zhengya,Zhang, Wensheng. SLAN: Similarity-aware aggregation network for embedding out-of-knowledge-graph entities[J]. NEUROCOMPUTING,2022,491:186-196.
APA Li, Mingda,Sun, Zhengya,&Zhang, Wensheng.(2022).SLAN: Similarity-aware aggregation network for embedding out-of-knowledge-graph entities.NEUROCOMPUTING,491,186-196.
MLA Li, Mingda,et al."SLAN: Similarity-aware aggregation network for embedding out-of-knowledge-graph entities".NEUROCOMPUTING 491(2022):186-196.

入库方式： OAI收割

来源：自动化研究所

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。