Poincaré Embeddings

Introduced by Nickel et al. in Poincaré Embeddings for Learning Hierarchical Representations

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.

Source: Poincaré Embeddings for Learning Hierarchical Representations

Read Paper See Code

Papers

Paper	Code	Results	Date	Stars

Tasks

Task	Papers	Share
Graph Embedding	1	100.00%

Usage Over Time

This feature is experimental; we are continuously improving our matching algorithm.

Components

Component	Type	Add Remove
🤖 No Components Found	You can add them if they exist; e.g. Mask R-CNN uses RoIAlign

Categories

Add Remove

Word Embeddings

Static Word Embeddings