Viet-Anh on Software Logo

What is: Poincaré Embeddings?

SourcePoincaré Embeddings for Learning Hierarchical Representations
Year2000
Data SourceCC BY-SA - https://paperswithcode.com

Poincaré Embeddings learn hierarchical representations of symbolic data by embedding them into hyperbolic space -- or more precisely into an nn-dimensional Poincaré ball. Due to the underlying hyperbolic geometry, this allows for learning of parsimonious representations of symbolic data by simultaneously capturing hierarchy and similarity. Embeddings are learnt based on Riemannian optimization.