Timezone: »
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) 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 reformulation 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.
Author Information
Timothee Lacroix (Facebook)
Nicolas Usunier (Facebook AI Research)
Guillaume Obozinski (Ecole des Ponts - ParisTech)
Related Events (a corresponding poster, oral, or spotlight)
-
2018 Oral: Canonical Tensor Decomposition for Knowledge Base Completion »
Wed. Jul 11th 02:50 -- 03:00 PM Room A5
More from the Same Authors
-
2022 Workshop: Responsible Decision Making in Dynamic Environments »
Virginie Do · Thorsten Joachims · Alessandro Lazaric · Joelle Pineau · Matteo Pirotta · Harsh Satija · Nicolas Usunier -
2020 Poster: Growing Action Spaces »
Gregory Farquhar · Laura Gustafson · Zeming Lin · Shimon Whiteson · Nicolas Usunier · Gabriel Synnaeve -
2020 Poster: Fully Parallel Hyperparameter Search: Reshaped Space-Filling »
Marie-Liesse Cauwet · Camille Couprie · Julien Dehos · Pauline Luc · Jeremy Rapin · Morgane Riviere · Fabien Teytaud · Olivier Teytaud · Nicolas Usunier -
2017 Workshop: Video Games and Machine Learning »
Gabriel Synnaeve · Julian Togelius · Tom Schaul · Oriol Vinyals · Nicolas Usunier -
2017 Poster: Parseval Networks: Improving Robustness to Adversarial Examples »
Moustapha Cisse · Piotr Bojanowski · Edouard Grave · Yann Dauphin · Nicolas Usunier -
2017 Talk: Parseval Networks: Improving Robustness to Adversarial Examples »
Moustapha Cisse · Piotr Bojanowski · Edouard Grave · Yann Dauphin · Nicolas Usunier