Klein Model for Hyperbolic Neural Networks
This work provides a third option for hyperbolic neural networks, which is incremental as it extends existing methods to a new coordinate representation.
The authors tackled the problem of modeling complex data structures by introducing a framework for hyperbolic neural networks based on the Klein model, showing numerically that it performs on par with the Poincaré ball model.
Hyperbolic neural networks (HNNs) have been proved effective in modeling complex data structures. However, previous works mainly focused on the Poincaré ball model and the hyperboloid model as coordinate representations of the hyperbolic space, often neglecting the Klein model. Despite this, the Klein model offers its distinct advantages thanks to its straight-line geodesics, which facilitates the well-known Einstein midpoint construction, previously leveraged to accompany HNNs in other models. In this work, we introduce a framework for hyperbolic neural networks based on the Klein model. We provide detailed formulation for representing useful operations using the Klein model. We further study the Klein linear layer and prove that the "tangent space construction" of the scalar multiplication and parallel transport are exactly the Einstein scalar multiplication and the Einstein addition, analogous to the Möbius operations used in the Poincaré ball model. We show numerically that the Klein HNN performs on par with the Poincaré ball model, providing a third option for HNN that works as a building block for more complicated architectures.