Poster
Poincaré Embeddings for Learning Hierarchical Representations
Maximillian Nickel · Douwe Kiela

Tue Dec 5th 06:30 -- 10:30 PM @ Pacific Ballroom #104 #None

Representation learning has become an invaluable approach for learning from symbolic data such as text and graphs. However, state-of-the-art embedding methods typically do not account for latent hierarchical structures which are characteristic for many complex symbolic datasets. In this work, we introduce a new approach for learning 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 us to learn parsimonious representations of symbolic data by simultaneously capturing hierarchy and similarity. We present an efficient algorithm to learn the embeddings based on Riemannian optimization and show experimentally that Poincaré embeddings can outperform Euclidean embeddings significantly on data with latent hierarchies, both in terms of representation capacity and in terms of generalization ability.

Author Information

Maximillian Nickel (Facebook)
Douwe Kiela (Facebook AI Research)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors