LibKGE - A knowledge graph embedding library for reproducible research

Samuel Broscheit, Daniel Ruffinelli, Adrian Kochsiek, Patrick Betz, Rainer Gemulla


Abstract
LibKGE ( https://github.com/uma-pi1/kge ) is an open-source PyTorch-based library for training, hyperparameter optimization, and evaluation of knowledge graph embedding models for link prediction. The key goals of LibKGE are to enable reproducible research, to provide a framework for comprehensive experimental studies, and to facilitate analyzing the contributions of individual components of training methods, model architectures, and evaluation methods. LibKGE is highly configurable and every experiment can be fully reproduced with a single configuration file. Individual components are decoupled to the extent possible so that they can be mixed and matched with each other. Implementations in LibKGE aim to be as efficient as possible without leaving the scope of Python/Numpy/PyTorch. A comprehensive logging mechanism and tooling facilitates in-depth analysis. LibKGE provides implementations of common knowledge graph embedding models and training methods, and new ones can be easily added. A comparative study (Ruffinelli et al., 2020) showed that LibKGE reaches competitive to state-of-the-art performance for many models with a modest amount of automatic hyperparameter tuning.
Anthology ID:
2020.emnlp-demos.22
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
Month:
October
Year:
2020
Address:
Online
Editors:
Qun Liu, David Schlangen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
165–174
Language:
URL:
https://aclanthology.org/2020.emnlp-demos.22
DOI:
10.18653/v1/2020.emnlp-demos.22
Bibkey:
Cite (ACL):
Samuel Broscheit, Daniel Ruffinelli, Adrian Kochsiek, Patrick Betz, and Rainer Gemulla. 2020. LibKGE - A knowledge graph embedding library for reproducible research. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 165–174, Online. Association for Computational Linguistics.
Cite (Informal):
LibKGE - A knowledge graph embedding library for reproducible research (Broscheit et al., EMNLP 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.emnlp-demos.22.pdf
Code
 uma-pi1/kge
Data
FB15k-237