Spotlight
Numerically Accurate Hyperbolic Embeddings Using Tiling-Based Models
Tao Yu · Christopher De Sa

Thu Dec 12th 04:15 -- 04:20 PM @ West Exhibition Hall B

Hyperbolic embeddings achieve excellent performance when embedding hierarchical data structures like synonym or type hierarchies, but they can be limited by numerical error when ordinary floating-point numbers are used to represent points in hyperbolic space. Standard models such as the Poincar{\'e} disk and the Lorentz model have unbounded numerical error as points get far from the origin. To address this, we propose a new model which uses an integer-based tiling to represent \emph{any} point in hyperbolic space with provably bounded numerical error. This allows us to learn high-precision embeddings without using BigFloats, and enables us to store the resulting embeddings with fewer bits. We evaluate our tiling-based model empirically, and show that it can both compress hyperbolic embeddings (down to $2\%$ of a Poincar{\'e} embedding on WordNet Nouns) and learn more accurate embeddings on real-world datasets.

Author Information

Tao Yu (Cornell University)
Christopher De Sa (Cornell)

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

More from the Same Authors