Peng, X. orcid.org/0000-0001-5787-9982, Chen, G., Lin, C. et al. (1 more author) (Submitted: 2021) Highly efficient knowledge graph embedding learning with orthogonal procrustes analysis. arXiv. (Submitted)
Abstract
Knowledge Graph Embeddings (KGEs) have been intensively explored in recent years due to their promise for a wide range of applications. However, existing studies focus on improving the final model performance without acknowledging the computational cost of the proposed approaches, in terms of execution time and environmental impact. This paper proposes a simple yet effective KGE framework which can reduce the training time and carbon footprint by orders of magnitudes compared with state-of-the-art approaches, while producing competitive performance. We highlight three technical innovations: full batch learning via relational matrices, closed-form Orthogonal Procrustes Analysis for KGEs, and non-negative-sampling training. In addition, as the first KGE method whose entity embeddings also store full relation information, our trained models encode rich semantics and are highly interpretable. Comprehensive experiments and ablation studies involving 13 strong baselines and two standard datasets verify the effectiveness and efficiency of our algorithm.
Metadata
Item Type: | Article |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2021 The Author(s). For reuse permissions, please contact the Author(s). |
Keywords: | cs.LG; cs.LG; cs.AI; cs.CL; stat.ML |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Computer Science (Sheffield) |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 21 Apr 2021 15:30 |
Last Modified: | 21 Apr 2021 15:32 |
Status: | Submitted |
Identification Number: | https://arxiv.org/abs/2104.04676 |
Related URLs: | |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:173332 |