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. 多媒体计算与图形学团队
TCKGE: Transformers with contrastive learning for knowledge graph embedding

文献类型：期刊论文

作者Zhang, Xiaowei2; Fang, Quan1; Hu, Jun1; Qian, Shengsheng1; Xu, Changsheng1
刊名INTERNATIONAL JOURNAL OF MULTIMEDIA INFORMATION RETRIEVAL
出版日期2022-11-27
页码9
ISSN号2192-6611
关键词Augmentation Contrastive learning Knowledge graph Transformer
DOI10.1007/s13735-022-00256-3
通讯作者Fang, Quan(qfang@nlpr.ia.ac.cn)
英文摘要Representation learning of knowledge graphs has emerged as a powerful technique for various downstream tasks. In recent years, numerous research efforts have been made for knowledge graphs embedding. However, previous approaches usually have difficulty dealing with complex multi-relational knowledge graphs due to their shallow network architecture. In this paper, we propose a novel framework named Transformers with Contrastive learning for Knowledge Graph Embedding (TCKGE), which aims to learn complex semantics in multi-relational knowledge graphs with deep architectures. To effectively capture the rich semantics of knowledge graphs, our framework leverages the powerful Transformers to build a deep hierarchical architecture to dynamically learn the embeddings of entities and relations. To obtain more robust knowledge embeddings with our deep architecture, we design a contrastive learning scheme to facilitate optimization by exploring the effectiveness of several different data augmentation strategies. The experimental results on two benchmark datasets show the superior of TCKGE over state-of-the-art models.
资助项目National Natural Science Foundation of China[62036012] ; National Natural Science Foundation of China[62072456] ; National Natural Science Foundation of China[62106262] ; Open Research Projects of Zhejiang Lab[2021KE0AB05]
WOS研究方向Computer Science
语种英语
出版者SPRINGER
WOS记录号WOS:000889032300001
资助机构National Natural Science Foundation of China ; Open Research Projects of Zhejiang Lab
源URL[http://ir.ia.ac.cn/handle/173211/50779]  
专题自动化研究所_模式识别国家重点实验室_多媒体计算与图形学团队
通讯作者Fang, Quan
作者单位1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
2.Zhengzhou Univ, Henan Inst Adv Technol, Zhengzhou 450001, Peoples R China
推荐引用方式
GB/T 7714		 Zhang, Xiaowei,Fang, Quan,Hu, Jun,et al. TCKGE: Transformers with contrastive learning for knowledge graph embedding[J]. INTERNATIONAL JOURNAL OF MULTIMEDIA INFORMATION RETRIEVAL,2022:9.
APA Zhang, Xiaowei,Fang, Quan,Hu, Jun,Qian, Shengsheng,&Xu, Changsheng.(2022).TCKGE: Transformers with contrastive learning for knowledge graph embedding.INTERNATIONAL JOURNAL OF MULTIMEDIA INFORMATION RETRIEVAL,9.
MLA Zhang, Xiaowei,et al."TCKGE: Transformers with contrastive learning for knowledge graph embedding".INTERNATIONAL JOURNAL OF MULTIMEDIA INFORMATION RETRIEVAL (2022):9.

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。