An End-to-End Training Method to Ensemble Bi-Linear Models for Knowledge Graph Completion

Si CEN, Han LIU, Chao LIU, Xiaoying ZOU, Guoquan DAI, Xizhao WANG*

*Corresponding author for this work

Research output: Book Chapters | Papers in Conference ProceedingsConference paper (refereed)Referred Conference Paperpeer-review

Abstract

The study of ensemble learning in knowledge graph embedding (KGE) shows that combining multiple individual KGE models can perform better on knowledge graph completion. However, existing KGE ensemble methods ignore the creation of model diversity because these methods independently train individual models, which are short of training interaction. To create rich model diversity, we propose a novel training method for ensemble bilinear models (EBM) for the problem of knowledge graph completion. EBM uses a weighted loss to allow individual KGE models to interact during training. In this way, the relations in the knowledge graph can be automatically modeled by the most appropriate model from the KGE individual ones. The experiments on knowledge graph completion show that EBM has richer diversity and performs better than the single bilinear model and the ensemble methods without interaction.

Original languageEnglish
Title of host publicationProceedings of 2023 International Conference on Machine Learning and Cybernetics, ICMLC 2023
PublisherIEEE Computer Society
Pages26-30
Number of pages5
ISBN (Electronic)9798350303780
DOIs
Publication statusPublished - 2023
Externally publishedYes
Event2023 International Conference on Machine Learning and Cybernetics, ICMLC 2023 - Adelaide, Australia
Duration: 9 Jul 202311 Jul 2023

Publication series

NameProceedings - International Conference on Machine Learning and Cybernetics
ISSN (Print)2160-133X
ISSN (Electronic)2160-1348

Conference

Conference2023 International Conference on Machine Learning and Cybernetics, ICMLC 2023
Country/TerritoryAustralia
CityAdelaide
Period9/07/2311/07/23

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

Keywords

  • Ensemble learning
  • Knowledge graph completion
  • Knowledge graph embedding
  • Weighted loss

Fingerprint

Dive into the research topics of 'An End-to-End Training Method to Ensemble Bi-Linear Models for Knowledge Graph Completion'. Together they form a unique fingerprint.

Cite this