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
AdaE: Knowledge Graph Embedding With Adaptive Embedding Sizes

文献类型：期刊论文

作者Guan, Zhanpeng1,2; Zhang, Fuwei3; Zhang, Zhao1; Zhuang, Fuzhen3,4; Wang, Fei1; An, Zhulin1; Xu, Yongjun1
刊名IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
出版日期2025-08-01
卷号37期号:8页码:4432-4445
关键词Knowledge graphs Adaptation models Training Data models Search problems Vectors Overfitting Tail Optimization Tensors Knowledge graph embedding (KGE) Data imbalance issue Dimension selection
ISSN号1041-4347
DOI10.1109/TKDE.2025.3566270
英文摘要Knowledge Graph Embedding (KGE) aims to learn dense embeddings as the representations for entities and relations in KGs. Indeed, the entities in existing KGs suffer from the data imbalance issue, i.e., there exists a substantial disparity in the occurrence frequencies among various entities. Existing KGE models pre-define a unified and fixed dimension size for all entity embeddings. However, embedding sizes of entities are highly desired for their frequencies, while a uniform embedding size may result in inadequate expression of entities, i.e., leading to overfitting for low-frequency entities and underfitting for high-frequency ones. A straight-forward idea is to set the embedding sizes for each entity before KGE training. However, manually selecting different embedding sizes is labor-intensive and time-consuming, posing challenges in real-world applications. To tackle this problem, we propose AdaE, which adaptively learns KG embeddings with different embedding sizes during training. In particular, AdaE is capable of selecting appropriate dimension sizes for each entity from a continuous integer space. To this end, we specially tailor bilevel optimization for the KGE task, which alternately learns representations and embedding sizes of entities. Our framework is general and flexible, fitting various existing KGE models. Extensive experiments demonstrate the effectiveness and compatibility of AdaE.
资助项目National Key Research and Development Program of China[2024YFF0729003] ; National Natural Science Foundation of China[62206266] ; National Natural Science Foundation of China[62176014] ; Fundamental Research Funds for the Central Universities
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:001525525600006
出版者IEEE COMPUTER SOC
源URL[http://119.78.100.204/handle/2XEOYT63/42038]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Zhang, Zhao
作者单位1.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
3.Beihang Univ, Inst Artificial Intelligence, Beijing 100191, Peoples R China
4.Zhongguancun Lab, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714		 Guan, Zhanpeng,Zhang, Fuwei,Zhang, Zhao,et al. AdaE: Knowledge Graph Embedding With Adaptive Embedding Sizes[J]. IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING,2025,37(8):4432-4445.
APA Guan, Zhanpeng.,Zhang, Fuwei.,Zhang, Zhao.,Zhuang, Fuzhen.,Wang, Fei.,...&Xu, Yongjun.(2025).AdaE: Knowledge Graph Embedding With Adaptive Embedding Sizes.IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING,37(8),4432-4445.
MLA Guan, Zhanpeng,et al."AdaE: Knowledge Graph Embedding With Adaptive Embedding Sizes".IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 37.8(2025):4432-4445.

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。