Improved Knowledge Graph Embedding Using Background Taxonomic Information

Authors

  • Bahare Fatemi University of British Columbia
  • Siamak Ravanbakhsh University of British Columbia
  • David Poole University of British Columbia

DOI:

https://doi.org/10.1609/aaai.v33i01.33013526

Abstract

Knowledge graphs are used to represent relational information in terms of triples. To enable learning about domains, embedding models, such as tensor factorization models, can be used to make predictions of new triples. Often there is background taxonomic information (in terms of subclasses and subproperties) that should also be taken into account. We show that existing fully expressive (a.k.a. universal) models cannot provably respect subclass and subproperty information. We show that minimal modifications to an existing knowledge graph completion method enables injection of taxonomic information. Moreover, we prove that our model is fully expressive, assuming a lower-bound on the size of the embeddings. Experimental results on public knowledge graphs show that despite its simplicity our approach is surprisingly effective.

Downloads

Published

2019-07-17

How to Cite

Fatemi, B., Ravanbakhsh, S., & Poole, D. (2019). Improved Knowledge Graph Embedding Using Background Taxonomic Information. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 3526-3533. https://doi.org/10.1609/aaai.v33i01.33013526

Issue

Section

AAAI Technical Track: Machine Learning