Sharing Parameter by Conjugation for Knowledge Graph Embeddings in Complex Space

Xincan Feng, Zhi Qu, Yuchang Cheng, Taro Watanabe, Nobuhiro Yugami


Abstract
A Knowledge Graph (KG) is the directed graphical representation of entities and relations in the real world. KG can be applied in diverse Natural Language Processing (NLP) tasks where knowledge is required. The need to scale up and complete KG automatically yields Knowledge Graph Embedding (KGE), a shallow machine learning model that is suffering from memory and training time consumption issues. To mitigate the computational load, we propose a parameter-sharing method, i.e., using conjugate parameters for complex numbers employed in KGE models. Our method improves memory efficiency by 2x in relation embedding while achieving comparable performance to the state-of-the-art non-conjugate models, with faster, or at least comparable, training time. We demonstrated the generalizability of our method on two best-performing KGE models 5E (CITATION) and ComplEx (CITATION) on five benchmark datasets.
Anthology ID:
2022.textgraphs-1.3
Volume:
Proceedings of TextGraphs-16: Graph-based Methods for Natural Language Processing
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Editors:
Dmitry Ustalov, Yanjun Gao, Alexander Panchenko, Marco Valentino, Mokanarangan Thayaparan, Thien Huu Nguyen, Gerald Penn, Arti Ramesh, Abhik Jana
Venue:
TextGraphs
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
25–34
Language:
URL:
https://aclanthology.org/2022.textgraphs-1.3
DOI:
Bibkey:
Cite (ACL):
Xincan Feng, Zhi Qu, Yuchang Cheng, Taro Watanabe, and Nobuhiro Yugami. 2022. Sharing Parameter by Conjugation for Knowledge Graph Embeddings in Complex Space. In Proceedings of TextGraphs-16: Graph-based Methods for Natural Language Processing, pages 25–34, Gyeongju, Republic of Korea. Association for Computational Linguistics.
Cite (Informal):
Sharing Parameter by Conjugation for Knowledge Graph Embeddings in Complex Space (Feng et al., TextGraphs 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.textgraphs-1.3.pdf
Code
 xincanfeng/dimension
Data
FB15k-237