Learning Representations for Hyper-Relational Knowledge Graphs

Harry Shomer, Wei Jin, Juanhui Li, Yao Ma, Hui Liu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Knowledge graphs (KGs) have gained prominence for their ability to learn representations for uni-relational facts. Recently, research has focused on modeling hyper-relational facts, which move beyond the restriction of uni-relational facts and allow us to represent more complex and real-world information. However, existing approaches for learning representations on hyper-relational KGs majorly focus on enhancing the communication from qualifiers to base triples while overlooking the flow of information from base triple to qualifiers. This can lead to suboptimal qualifier representations, especially when a large amount of qualifiers are presented. It motivates us to design a framework that utilizes multiple aggregators to learn representations for hyper-relational facts: one from the perspective of the base triple and the other one from the perspective of the qualifiers. Experiments demonstrate the effectiveness of our framework for hyper-relational knowledge graph completion across multiple datasets. Furthermore, we conduct an ablation study that validates the importance of the various components in our framework.

Original languageEnglish (US)
Title of host publicationProceedings of the 2023 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2023
EditorsB. Aditya Prakash, Dong Wang, Tim Weninger
PublisherAssociation for Computing Machinery, Inc
Pages253-257
Number of pages5
ISBN (Electronic)9798400704093
DOIs
StatePublished - Nov 6 2023
Externally publishedYes
Event15th IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2023 - Kusadasi, Turkey
Duration: Nov 6 2023Nov 9 2023

Publication series

NameProceedings of the 2023 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2023

Conference

Conference15th IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2023
Country/TerritoryTurkey
CityKusadasi
Period11/6/2311/9/23

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Computer Networks and Communications
  • Information Systems
  • Information Systems and Management
  • Safety, Risk, Reliability and Quality
  • Social Psychology
  • Communication

Keywords

  • knowledge graphs
  • link prediction

Fingerprint

Dive into the research topics of 'Learning Representations for Hyper-Relational Knowledge Graphs'. Together they form a unique fingerprint.

Cite this