On Inductive Abilities of Latent Factor Models for Relational Learning

Abstract

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 they 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 genealogies. Based on these experimental results, we propose new research directions to improve on existing models.

Cite

Text

Trouillon et al. "On Inductive Abilities of Latent Factor Models for Relational Learning." Journal of Artificial Intelligence Research, 2019. doi:10.1613/JAIR.1.11305

Markdown

[Trouillon et al. "On Inductive Abilities of Latent Factor Models for Relational Learning." Journal of Artificial Intelligence Research, 2019.](https://mlanthology.org/jair/2019/trouillon2019jair-inductive/) doi:10.1613/JAIR.1.11305

BibTeX

@article{trouillon2019jair-inductive,
  title     = {{On Inductive Abilities of Latent Factor Models for Relational Learning}},
  author    = {Trouillon, Théo and Gaussier, Éric and Dance, Christopher R. and Bouchard, Guillaume},
  journal   = {Journal of Artificial Intelligence Research},
  year      = {2019},
  pages     = {21-53},
  doi       = {10.1613/JAIR.1.11305},
  volume    = {64},
  url       = {https://mlanthology.org/jair/2019/trouillon2019jair-inductive/}
}