Poincaré Embeddings

2000년 도입 · 논문 1편에서 사용

Poincaré Embeddings learn hierarchical representations of symbolic data by embedding them into hyperbolic space -- or more precisely into an $n$-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.

출처: Poincaré Embeddings for Learning Hierarchical Representations

소개 논문: Poincaré Embeddings for Learning Hierarchical Representations