Translating Embeddings for Modeling Multi-relational Data

Antoine Bordes (1, 2) , Nicolas Usunier (1, 2) , Alberto Garcia-Duran (1) , Jason Weston (3) , Oksana Yakhnenko (3)

1 Heudiasyc - Heuristique et Diagnostic des Systèmes Complexes [Compiègne]
2 Labex MS2T - Laboratoire d'Excellence "Maîtrise des Systèmes de Systèmes Technologiques"
3 Google Inc

We consider the problem of embedding entities and relationships of multi- relational data in low-dimensional vector spaces. Our objective is to propose a canonical model which is easy to train, contains a reduced number of parameters and can scale up to very large databases. Hence, we propose TransE, a method which models relationships by interpreting them as translations operating on the low-dimensional embeddings of the entities. Despite its simplicity, this assump- tion proves to be powerful since extensive experiments show that TransE significantly outperforms state-of-the-art methods in link prediction on two knowledge bases. Besides, it can be successfully trained on a large scale data set with 1M entities, 25k relationships and more than 17M training samples.

Domaines: Apprentissage [cs.LG]

Antoine Bordes, Nicolas Usunier, Alberto Garcia-Duran, Jason Weston, Oksana Yakhnenko. Translating Embeddings for Modeling Multi-relational Data. Neural Information Processing Systems (NIPS), Dec 2013, South Lake Tahoe, United States. pp.1-9. ⟨hal-00920777⟩