LightCAKE: A Lightweight Framework for Context-Aware Knowledge Graph Embedding

被引:6
|
作者
Ning, Zhiyuan [1 ,2 ]
Qiao, Ziyue [1 ,2 ]
Dong, Hao [1 ,2 ]
Du, Yi [1 ]
Zhou, Yuanchun [1 ]
机构
[1] Chinese Acad Sci, Comp Network Informat Ctr, Beijing, Peoples R China
[2] Univ Chinese Acad Sci, Beijing, Peoples R China
来源
ADVANCES IN KNOWLEDGE DISCOVERY AND DATA MINING, PAKDD 2021, PT III | 2021年 / 12714卷
基金
北京市自然科学基金;
关键词
Knowledge graph embedding; Lightweight; Graph context;
D O I
10.1007/978-3-030-75768-7_15
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Knowledge graph embedding (KGE) models learn to project symbolic entities and relations into a continuous vector space based on the observed triplets. However, existing KGE models cannot make a proper trade-off between the graph context and the model complexity, which makes them still far from satisfactory. In this paper, we propose a lightweight framework named LightCAKE for context-aware KGE. LightCAKE explicitly models the graph context without introducing redundant trainable parameters, and uses an iterative aggregation strategy to integrate the context information into the entity/relation embeddings. As a generic framework, it can be used with many simple KGE models to achieve excellent results. Finally, extensive experiments on public benchmarks demonstrate the efficiency and effectiveness of our framework.
引用
收藏
页码:181 / 193
页数:13
相关论文
共 50 条
  • [1] Context-Aware Temporal Knowledge Graph Embedding
    Liu, Yu
    Hua, Wen
    Xin, Kexuan
    Zhou, Xiaofang
    WEB INFORMATION SYSTEMS ENGINEERING - WISE 2019, 2019, 11881 : 583 - 598
  • [2] CAKE: A Context-Aware Knowledge Embedding Model of Knowledge Graph
    Chen, Jiadong
    Ke, Hua
    Mo, Haijian
    Gao, Xiaofeng
    Chen, Guihai
    DATABASE AND EXPERT SYSTEMS APPLICATIONS, DEXA 2022, PT I, 2022, 13426 : 48 - 62
  • [3] Context-Aware Service Recommendation Based on Knowledge Graph Embedding
    Mezni, Haithem
    Benslimane, Djamal
    Bellatreche, Ladjel
    IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2022, 34 (11) : 5225 - 5238
  • [4] A Lightweight Knowledge Graph Embedding Framework for Efficient Inference and Storage
    Wang, Haoyu
    Wang, Yaqing
    Lian, Defu
    Gao, Jing
    PROCEEDINGS OF THE 30TH ACM INTERNATIONAL CONFERENCE ON INFORMATION & KNOWLEDGE MANAGEMENT, CIKM 2021, 2021, : 1909 - 1918
  • [5] Learning graph attention-aware knowledge graph embedding
    Li, Chen
    Peng, Xutan
    Niu, Yuhang
    Zhang, Shanghang
    Peng, Hao
    Zhou, Chuan
    Li, Jianxin
    NEUROCOMPUTING, 2021, 461 : 516 - 529
  • [6] Temporal knowledge completion with context-aware embeddings
    Yu Liu
    Wen Hua
    Jianfeng Qu
    Kexuan Xin
    Xiaofang Zhou
    World Wide Web, 2021, 24 : 675 - 695
  • [7] Temporal knowledge completion with context-aware embeddings
    Liu, Yu
    Hua, Wen
    Qu, Jianfeng
    Xin, Kexuan
    Zhou, Xiaofang
    WORLD WIDE WEB-INTERNET AND WEB INFORMATION SYSTEMS, 2021, 24 (02): : 675 - 695
  • [8] Knowledge graph confidence-aware embedding for recommendation
    Huang, Chen
    Yu, Fei
    Wan, Zhiguo
    Li, Fengying
    Ji, Hui
    Li, Yuandi
    NEURAL NETWORKS, 2024, 180
  • [9] Triple Context-Based Knowledge Graph Embedding
    Gao, Huan
    Shi, Jun
    Qi, Guilin
    Wang, Meng
    IEEE ACCESS, 2018, 6 : 58978 - 58989
  • [10] Asymmetric Neighboring Context Modeling for Knowledge Graph Embedding
    Hu, Yuanhao
    Ouyang, Yuanxin
    Bai, Jun
    Wang, Chuanrui
    Rong, Wenge
    Xiong, Zhang
    KNOWLEDGE SCIENCE, ENGINEERING AND MANAGEMENT, PT I, 2022, 13368 : 683 - 695