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 |
DOI | 10.1016/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。