Journal of Intelligent Information Systems

, Volume 47, Issue 1, pp 91–109

Efficient energy-based embedding models for link prediction in knowledge graphs

  • Pasquale Minervini
  • Claudia d’Amato
  • Nicola Fanizzi
Article

DOI: 10.1007/s10844-016-0414-7

Cite this article as:
Minervini, P., d’Amato, C. & Fanizzi, N. J Intell Inf Syst (2016) 47: 91. doi:10.1007/s10844-016-0414-7

Abstract

We focus on the problem of link prediction in Knowledge Graphs, with the goal of discovering new facts. To this purpose, Energy-Based Models for Knowledge Graphs that embed entities and relations in continuous vector spaces have been largely used. The main limitation in their applicability lies in the parameter learning phase, which may require a large amount of time for converging to optimal solutions. In this article, we first propose an unified view on different Energy-Based Embedding Models. Hence, for improving the model training phase, we propose the adoption of adaptive learning rates. We show that, by adopting adaptive learning rates during training, we can improve the efficiency of the parameter learning process by an order of magnitude, while leading to more accurate link prediction models in a significantly lower number of iterations. We extensively evaluate the proposed learning procedure on a variety of new models: our result show a significant improvement over state-of-the-art link prediction methods on two large Knowledge Graphs, namely WordNet and Freebase.

Keywords

Energy-based embedding models Link predictions RDF knowledge graphs 

Copyright information

© Springer Science+Business Media New York 2016

Authors and Affiliations

  • Pasquale Minervini
    • 1
  • Claudia d’Amato
    • 1
  • Nicola Fanizzi
    • 1
  1. 1.Department of Computer ScienceUniversity of BariBariItaly