Augmenting and Tuning Knowledge Graph Embeddings

Knowledge graph embeddings rank among the most successful methods for link prediction in knowledge graphs, i.e., the task of completing an incomplete collection of relational facts. A downside of these models is their strong sensitivity to model hyperparameters, in particular regularizers, which hav...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Bamler, Robert, Salehi, Farnood, Mandt, Stephan
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 01.07.2019
Subjects
Tuning
Online AccessGet full text

Cover

More Information
Summary:Knowledge graph embeddings rank among the most successful methods for link prediction in knowledge graphs, i.e., the task of completing an incomplete collection of relational facts. A downside of these models is their strong sensitivity to model hyperparameters, in particular regularizers, which have to be extensively tuned to reach good performance [Kadlec et al., 2017]. We propose an efficient method for large scale hyperparameter tuning by interpreting these models in a probabilistic framework. After a model augmentation that introduces per-entity hyperparameters, we use a variational expectation-maximization approach to tune thousands of such hyperparameters with minimal additional cost. Our approach is agnostic to details of the model and results in a new state of the art in link prediction on standard benchmark data.
ISSN:2331-8422