ISA-KGC: Integrated Semantics-Structure Analysis in Knowledge Graph Completion

This paper presents Integrated Semantics-Structure Analysis in Knowledge Graph Completion (ISA-KGC), a new framework for Knowledge Graph Completion (KGC) aimed at addressing the incompleteness of knowledge graphs (KGs). ISA-KGC integrates Graph Neural Networks (GNN) with Transformer-based models, ef...

Full description

Saved in:
Bibliographic Details
Published inIEEE access Vol. 12; pp. 57250 - 57260
Main Authors Liu, Xingyu, Wang, Zhenxing, Sun, Yue, Han, Junmei, Xiao, Gang, Jiang, Jianchun
Format Journal Article
LanguageEnglish
Published Piscataway IEEE 2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects
Adaptation models
Graph neural network
Graph neural networks
Graphs
knowledge graph completion
knowledge graph embedding
Knowledge graphs
Knowledge representation
Metalearning
Performance measurement
pre-trained language model
Semantics
Structural analysis
Task analysis
Vectors
Online AccessGet full text

Cover

More Information
Summary:This paper presents Integrated Semantics-Structure Analysis in Knowledge Graph Completion (ISA-KGC), a new framework for Knowledge Graph Completion (KGC) aimed at addressing the incompleteness of knowledge graphs (KGs). ISA-KGC integrates Graph Neural Networks (GNN) with Transformer-based models, effectively blending structural and semantic information within Knowledge Graphs. This fusion enhances comprehension of KGs beyond what traditional methods offer. The framework utilizes Knowledge Graph Embedding (KGE) models, with GNN employed to augment these models, thus enhancing the overall analysis and interpretation of Knowledge Graphs. The effectiveness of ISA-KGC is validated through benchmark datasets FB15K-237 and WN18RR, showing notable improvements in performance metrics like hit@10 compared to existing methods.
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2024.3384533