147 citations · 382 across the 10 of their papers we have counts for
4 papers · 1 filter
Poincaré GloVe: Hyperbolic Word Embeddings
Alexandru Tifrea, Gary Bécigneul, Octavian-Eugen Ganea
Words are not created equal. In fact, they form an aristocratic graph with a latent hierarchical structure that the next generation of unsupervised learned word embeddings should r…
Riemannian Adaptive Optimization Methods
Gary Bécigneul, Octavian-Eugen Ganea
Several first order stochastic optimization methods commonly used in the Euclidean domain such as stochastic gradient descent (SGD), accelerated gradient descent or variance reduce…
Hyperbolic Neural Networks
Octavian-Eugen Ganea, Gary Bécigneul, Thomas Hofmann
Hyperbolic spaces have recently gained momentum in the context of machine learning due to their high capacity and tree-likeliness properties. However, the representational power of…
Hyperbolic Entailment Cones for Learning Hierarchical Embeddings
Octavian-Eugen Ganea, Gary Bécigneul, Thomas Hofmann
Learning graph representations via low-dimensional embeddings that preserve relevant network properties is an important class of problems in machine learning. We here present a nov…