EUVIMEDEUVIMED entdecken
Crossref

Hyper-node Relational Graph Attention Network for Multi-modal Knowledge Graph Completion

Shuang Liang, Anjie Zhu, Jiasheng Zhang, Jie Shao

ACM Transactions on Multimedia Computing, Communications, and Applications · 31.05.2023 · 19 (2) · 1-21

DOI: 10.1145/3545573 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Multimedia Computing, Communications, and Applications, online erschienen am 06.02.2023. Verfasst von Shuang Liang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 64-mal zitiert (Crossref) und nennt 54 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Shenzhen Science and Technology Program, Zhejiang Lab’s International Talent Fund for Young Professionals.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Knowledge graphs often suffer from incompleteness, and knowledge graph completion (KGC) aims at inferring the missing triplets through knowledge graph embedding from known factual triplets. However, most existing knowledge graph embedding methods only use the relational information of knowledge graph and treat the entities and relations as IDs with simple embedding layer, ignoring the multi-modal information among triplets, such as text descriptions, images, etc. In this work, we propose a novel network to incorporate different modal information with graph structure information for more precise representation of multi-modal knowledge graph, termed as hyper-node relational graph attention (HRGAT) network. In HRGAT, we use low-rank multi-modal fusion to model the intra-modality and inter-modality dynamics, which transforms the original knowledge graph to a hyper-node graph. Then, relational graph attention (RGAT) network is used, which contains relation-specific attention and entity-relation fusion operation to capture the graph structure information. Finally, we aggregate the updated multi-modal information and graph structure information to generate the final embeddings of knowledge graph to achieve KGC. By exploring multi-modal information and graph structure information, HRGAT embraces faster convergence speed and achieves the state-of-the-art for KGC on the standard datasets. Implementation code is available at https://github.com/broliang/HRGAT.

Förderung

  • National Natural Science Foundation of China
  • Shenzhen Science and Technology Program
  • Zhejiang Lab’s International Talent Fund for Young Professionals

Zitieren

APA

Liang, S., Zhu, A., Zhang, J., & Shao, J. (2023). Hyper-node Relational Graph Attention Network for Multi-modal Knowledge Graph Completion. ACM Transactions on Multimedia Computing, Communications, and Applications, 19(2), 1-21. https://doi.org/10.1145/3545573

Vancouver

Liang S, Zhu A, Zhang J, Shao J. Hyper-node Relational Graph Attention Network for Multi-modal Knowledge Graph Completion. ACM Transactions on Multimedia Computing, Communications, and Applications. 2023;19(2):1-21. doi:10.1145/3545573

BibTeX
@article{Liang2023,
  author = {Liang, Shuang and Zhu, Anjie and Zhang, Jiasheng and Shao, Jie},
  title = {Hyper-node Relational Graph Attention Network for Multi-modal Knowledge Graph Completion},
  journal = {ACM Transactions on Multimedia Computing, Communications, and Applications},
  year = {2023},
  volume = {19},
  number = {2},
  pages = {1--21},
  doi = {10.1145/3545573}
}
Kostenlos starten →