Canonical Tensor Decomposition for Knowledge Base Completion - École des Ponts ParisTech Access content directly
Journal Articles Proceedings of the 35th International Conference on Machine Learning Year : 2018

Canonical Tensor Decomposition for Knowledge Base Completion

Abstract

The problem of Knowledge Base Completion can be framed as a 3rd-order binary tensor completion problem. In this light, the Canonical Tensor Decomposition (CP) (Hitchcock, 1927) seems like a natural solution; however, current implementations of CP on standard Knowledge Base Completion benchmarks are lagging behind their competitors. In this work, we attempt to understand the limits of CP for knowledge base completion. First, we motivate and test a novel regularizer, based on tensor nuclear p-norms. Then, we present a refor-mulation of the problem that makes it invariant to arbitrary choices in the inclusion of predicates or their reciprocals in the dataset. These two methods combined allow us to beat the current state of the art on several datasets with a CP decomposition , and obtain even better results using the more advanced ComplEx model.
Fichier principal
Vignette du fichier
paper.pdf (405.73 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01817595 , version 1 (18-06-2018)

Identifiers

Cite

Timothée Lacroix, Nicolas Usunier, Guillaume Obozinski. Canonical Tensor Decomposition for Knowledge Base Completion. Proceedings of the 35th International Conference on Machine Learning, 2018, 80, pp.2863-2872. ⟨10.48550/arXiv.1806.07297⟩. ⟨hal-01817595⟩
179 View
83 Download

Altmetric

Share

Gmail Facebook X LinkedIn More