article · IEEE Access · 2020

Hamming Distance Encoding Multihop Relation Knowledge Graph Completion

Panfeng Chen, Yisong Wang, Quan Yu, Yi Han Fan, Renyan Feng

Cited by 9Open access

Abstract

Knowledge graphs (KGs) play an important role in many real-world applications like information retrieval, question answering, relation extraction, etc. To reveal implicit knowledge from a knowledge graph (KG), viz. knowledge graph completion (KGC), is a crucial task for the downstream applications based on KG. For this purpose various embedding-based approaches have been proposed recently. This paper proposes a new approach named HRESCAL to KGC. It extends the well-known embedding-based approach RESCAL by introducing Hamming distance-based encoder to capture implicit multihop and partial inverse relation features in a KG. Experimental results on widely used KGC benchmarks show that the new approach achieves state-of-the-art or is competitive AUC performance.

Cite this paper

APA 7

Chen, P., Wang, Y., Yu, Q., Fan, Y. H., & Feng, R. (2020). Hamming Distance Encoding Multihop Relation Knowledge Graph Completion. IEEE Access, 8, 117146–117158. https://doi.org/10.1109/access.2020.3004448

MLA 9

Chen, Panfeng, et al. “Hamming Distance Encoding Multihop Relation Knowledge Graph Completion.” IEEE Access, vol. 8, 2020, pp. 117146–58, https://doi.org/10.1109/access.2020.3004448.

Chicago

Chen, Panfeng, Yisong Wang, Quan Yu, Yi Han Fan, and Renyan Feng. 2020. “Hamming Distance Encoding Multihop Relation Knowledge Graph Completion.” IEEE Access 8: 117146–58. https://doi.org/10.1109/access.2020.3004448.

Harvard

Chen, P. et al. (2020) ‘Hamming Distance Encoding Multihop Relation Knowledge Graph Completion’, IEEE Access, 8, pp. 117146–117158. Available at: https://doi.org/10.1109/access.2020.3004448.

BibTeX

@article{chen2020hamming,
  title = {{Hamming Distance Encoding Multihop Relation Knowledge Graph Completion}},
  author = {Chen, Panfeng and Wang, Yisong and Yu, Quan and Fan, Yi Han and Feng, Renyan},
  journal = {IEEE Access},
  volume = {8},
  pages = {117146--117158},
  year = {2020},
  doi = {10.1109/access.2020.3004448}
}

Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.