1.1k citations · 1.2k across the 6 of their papers we have counts for
7 papers
On Inductive Abilities of Latent Factor Models for Relational Learning
Théo Trouillon, Éric Gaussier, Christopher R. Dance +1
Latent factor models are increasingly popular for modeling multi-relational knowledge graphs. By their vectorial nature, it is not only hard to interpret why this class of models w…
Complex and Holographic Embeddings of Knowledge Graphs: A Comparison
Théo Trouillon, Maximilian Nickel
Embeddings of knowledge graphs have received significant attention due to their excellent performance for tasks like link prediction and entity resolution. In this short paper, we…
Knowledge Graph Completion via Complex Tensor Factorization
Théo Trouillon, Christopher R. Dance, Johannes Welbl +3
In statistical relational learning, knowledge graph completion deals with automatically understanding the structure of large knowledge graphs---labeled directed graphs---and predic…
Complex Embeddings for Simple Link Prediction
Théo Trouillon, Johannes Welbl, Sebastian Riedel +2
In statistical relational learning, the link prediction problem is key to automatically understand the structure of large knowledge bases. As in previous studies, we propose to sol…
Decomposing Real Square Matrices via Unitary Diagonalization
Théo Trouillon, Christopher R. Dance, Éric Gaussier +1
Diagonalization, or eigenvalue decomposition, is very useful in many areas of applied mathematics, including signal processing and quantum physics. Matrix decomposition is also a u…
Online Learning to Sample
Guillaume Bouchard, Théo Trouillon, Julien Perez +1
Stochastic Gradient Descent (SGD) is one of the most widely used techniques for online optimization in machine learning. In this work, we accelerate SGD by adaptively learning how…
Fast Inference of Admixture Coefficients Using Sparse Non-negative Matrix Factorization Algorithms
Eric Frichot, François Mathieu, Théo Trouillon +2
Inference of individual admixture coefficients, which is important for population genetic and association studies, is commonly performed using compute-intensive likelihood algorith…