Abstract
Publications home
On inductive abilities of latent factor models for relational learning
at
| Theo Trouillon, Eric Gaussier, Christopher Dance, Guillaume Bouchard |
| Journal of Artificial Intelligence Research, 64, pp. 21-53 |
| Download |
| Download |
@article{trouillon2019inductive,
title={On inductive abilities of latent factor models for relational learning},
author={Trouillon, Th{\'e}o and Gaussier, {\'E}ric and Dance, Christopher R and Bouchard, Guillaume},
journal={Journal of Artificial Intelligence Research},
volume={64},
pages={21--53},
year={2019}
}Latent factor models are increasingly popular for modeling multi-relational knowledge graphs. By their vectorial nature, it is not only hard to interpret why this class of models works so well, but also to understand where they fail and how the might be improved. We conduct an experimental survey of state-of-the-art models, not towards a purely comparative end, but as a means to get insight about their inductive abilities. To assess the strengths and weaknesses of each model, we create simple tasks that exhibit first atomic properties of binary relations, and then common inter-relational inference through synthetic families. Based on these experimental results, we propose new research directions to improve on existing models.
This web site uses cookies for the site search, to display videos and for aggregate site analytics.
Learn more about these cookies in our privacy notice.
Cookie settings
You may choose which kind of cookies you allow when visiting this website. Click on "Save cookie settings" to apply your choice.
This content is currently blocked. To view the content please either 'Accept social media cookies' or 'Accept all cookies'.
For more information on cookies see our privacy notice.