Node Co-occurrence based Graph Neural Networks for Knowledge Graph Link Prediction

被引:6
|
作者
Nguyen, Dai Quoc [1 ]
Vinh Tong [2 ]
Phung, Dinh [3 ]
Dat Quoc Nguyen [2 ]
机构
[1] Oracle Labs, Brisbane, Qld, Australia
[2] VinAI Res, Hanoi, Vietnam
[3] Monash Univ, Clayton, Vic, Australia
关键词
graph neural networks; knowledge graph completion; quaternion;
D O I
10.1145/3488560.3502183
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We introduce a novel embedding model, named NoGE, which aims to integrate co-occurrence among entities and relations into graph neural networks to improve knowledge graph completion (i.e., link prediction). Given a knowledge graph, NoGE constructs a single graph considering entities and relations as individual nodes. NoGE then computes weights for edges among nodes based on the co-occurrence of entities and relations. Next, NoGE proposes Dual Quaternion Graph Neural Networks (DualQGNN) and utilizes DualQGNN to update vector representations for entity and relation nodes. NoGE then adopts a score function to produce the triple scores. Comprehensive experimental results show that NoGE obtains state-of-the-art results on three new and difficult benchmark datasets CoDEx for knowledge graph completion.
引用
收藏
页码:1589 / 1592
页数:4
相关论文
共 50 条
  • [31] The Research of Link Prediction in Knowledge Graph based on Distance Constraint
    Wei, Linlu
    Liu, Fangfang
    [J]. 2020 IEEE 13TH INTERNATIONAL CONFERENCE ON SERVICES COMPUTING (SCC 2020), 2020, : 68 - 75
  • [32] Explaining Link Prediction Systems based on Knowledge Graph Embeddings
    Rossi, Andrea
    Firmani, Donatella
    Merialdo, Paolo
    Teofili, Tommaso
    [J]. PROCEEDINGS OF THE 2022 INTERNATIONAL CONFERENCE ON MANAGEMENT OF DATA (SIGMOD '22), 2022, : 2062 - 2075
  • [33] Approach for link prediction of knowledge graph based on probabilistic inferences
    Yao, Jianjun
    Li, Jianyu
    Yue, Kun
    Duan, Liang
    Fu, Xiaodong
    [J]. Jisuanji Jicheng Zhizao Xitong/Computer Integrated Manufacturing Systems, CIMS, 2023, 29 (10): : 3483 - 3495
  • [34] A Robust Comparative Analysis of Graph Neural Networks on Dynamic Link Prediction
    Skarding, Joakim
    Hellmich, Matthew
    Gabrys, Bogdan
    Musial, Katarzyna
    [J]. IEEE ACCESS, 2022, 10 : 64146 - 64160
  • [35] A Recommendation Algorithm for Collaborative Conceptual Modeling Based on Co-occurrence Graph
    Fu, Kai
    Wang, Shijun
    Zhao, Haiyan
    Zhang, Wei
    [J]. REQUIREMENTS ENGINEERING IN THE BIG DATA ERA, 2015, 558 : 51 - 63
  • [36] Asymmetric Learning for Graph Neural Network based Link Prediction
    Yao, Kai-Lang
    Li, Wu-Jun
    [J]. ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA, 2024, 18 (05)
  • [37] Implementing link prediction in protein networks via feature fusion models based on graph neural networks
    Zhang, Chi
    Gao, Qian
    Li, Ming
    Yu, Tianfei
    [J]. COMPUTATIONAL BIOLOGY AND CHEMISTRY, 2024, 108
  • [38] Community knowledge graph abstraction for enhanced link prediction: A study on PubMed knowledge graph
    Zhao, Yang
    Bollegala, Danushka
    Hirose, Shunsuke
    Jin, Yingzi
    Kozu, Tomotake
    [J]. JOURNAL OF BIOMEDICAL INFORMATICS, 2024, 158
  • [39] A Survey on Knowledge Graph Embeddings for Link Prediction
    Wang, Meihong
    Qiu, Linling
    Wang, Xiaoli
    [J]. SYMMETRY-BASEL, 2021, 13 (03):
  • [40] Fuzzy Search of Knowledge Graph with Link Prediction
    Ugai, Takanori
    [J]. PROCEEDINGS OF THE 10TH INTERNATIONAL JOINT CONFERENCE ON KNOWLEDGE GRAPHS (IJCKG 2021), 2021, : 121 - 125