Blending of Two and Three-way Interactions for Modeling Multi-relational Data

Alberto García-Durán (1) , Antoine Bordes (2) , Nicolas Usunier (1, 3)

1 Heudiasyc - Heuristique et Diagnostic des Systèmes Complexes [Compiègne]
2 FAIR - Facebook AI Research [Paris]
3 Labex MS2T - Laboratoire d'Excellence "Maîtrise des Systèmes de Systèmes Technologiques"

Much work has been recently proposed to model relational data, especially in the multi-relational case, where di↵erent kinds of relationships are used to connect the various data entities. Previous attempts either consist of powerful systems with high capacity to model complex connectivity patterns, which unfortunately usually end up overfitting on rare relationships, or in approaches that trade capacity for simplicity in order to fairly model all relationships, frequent or not. In this paper, we propose a happy medium obtained by complementing a high-capacity model with a simpler one, both pre-trained separately and jointly fine-tuned. We show that our approach outperforms existing models on different types of relationships, and achieves state-of-the-art results on two benchmarks of the literature.

Domaines: Informatique [cs]

Alberto García-Durán, Antoine Bordes, Nicolas Usunier. Blending of Two and Three-way Interactions for Modeling Multi-relational Data. Machine Learning and Knowledge Discovery in Databases - European Conference ECML/PKDD, Sep 2014, Nancy, France. ⟨hal-01131957⟩