arrow
返回

HoGRN: Explainable Sparse Knowledge Graph Completion via High-Order Graph Reasoning Network

delete2024-12-01
delete0
PRE
AI
W
Weijian Chen
Y
Yixin Cao
冯
冯福利 (Fuli Feng)
Xiangnan He 封面图
Xiangnan He (Xiangnan He)
张
张勇东 (Yongdong Zhang) *
DOI:10.1109/TKDE.2024.3422226delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
Knowledge Graphs (KGs) are becoming increasingly essential infrastructures in many applications while suffering from incompleteness issues. The KG Completion (KGC) task automatically predicts missing facts based on an incomplete KG. However, existing methods perform unsatisfactorily in real-world scenarios. On the one hand, their performance will dramatically degrade along with the increasing sparsity of KGs. On the other hand, the inference procedure for prediction is an untrustworthy black box. This paper proposes a novel explainable model for sparse KGC, compositing high-order reasoning into a Graph Convolutional Network (GCN), namely HoGRN. It can not only improve the generalization ability to mitigate the information insufficiency issue but also provide interpretability while maintaining the model's effectiveness and efficiency. Two main components are seamlessly integrated for joint optimization. First, the high-order reasoning component learns high-quality relation representations by capturing endogenous correlation among relations. This can reflect logical rules to justify a broader range of missing facts. Second, the entity updating component leverages a weight-free GCN to efficiently model KG structures with interpretability. For evaluation, we conduct extensive experiments-the results of HoGRN on several sparse KGs present considerable improvements. Further ablation and case studies demonstrate the effectiveness of the main components.
Keyword:
Cognition
Tail
Vectors
Task analysis
Semantics
Reinforcement learning
Knowledge graphs
Knowledge graph
link prediction
relational reasoning
graph convolutional network
interpretability

期刊

IEEE Transactions on Knowledge and Data Engineering 封面图
IEEE Transactions on Knowledge and Data Engineering
IF:
10.4
论文数:
6.9K
被引数:
3.2W

机构

F
fudan university
学者数:
11.8W
论文数: 7.7W
被引数: 121
U
university of science & technology of china, cas
学者数:
3.2W
论文数: 2.7W
被引数: 74
C
chinese academy of sciences
学者数:
56.7W
论文数: 45.0W
被引数: 704
学者 查看更多机构
引用论文

引用论文

OBSTETRIC ULTRASONOGRAPHY
err1997-06-01
err0
PREAI
errMark E. Deutchman; Ricardo Hahn
err分享
err收藏
Impact of Age at Administration, Lysosomal Storage, and Transgene Regulatory Elements on AAV2/8-Mediated Rat Liver Transduction
err2012-03-13
err0
errOAAI
errGabriella Cotugno; Patrizia Annunziata; Maria Vittoria Barone; Marianthi Karali; Sandro Banfi; Alberto Auricchio
err分享
err收藏
“Pomacytosis”—Semi-extracellular phagocytosis of cyanobacteria by the smallest marine algae
err2018-01-05
err0
errOAAI
errNina A. Kamennaya; Gabrielle Kennaway; Bernhard M. Fuchs; Mikhail V. Zubkov
err分享
err收藏
err分享
err收藏
Multiplex secretome engineering enhances recombinant protein production and purity
err
IF0
err2019-05-24
err0
errOAAI
errStefan Kol; Daniel Ley; Tune Wulff; Marianne Decker; Johnny Arnsdorf; Jahir M. Gutierrez; Austin W.T. Chiang; Lasse Ebdrup Pedersen; Helene Faustrup Kildegaard; Gyun Min Lee; Nathan E. Lewis
err分享
err收藏
err分享
err收藏
学者 查看更多内容