Lorentzian Distance Learning for Hyperbolic Representations
[edit]
Proceedings of the 36th International Conference on Machine Learning, PMLR 97:36723681, 2019.
Abstract
We introduce an approach to learn representations based on the Lorentzian distance in hyperbolic geometry. Hyperbolic geometry is especially suited to hierarchicallystructured datasets, which are prevalent in the real world. Current hyperbolic representation learning methods compare examples with the PoincarĂ© distance. They try to minimize the distance of each node in a hierarchy with its descendants while maximizing its distance with other nodes. This formulation produces node representations close to the centroid of their descendants. To obtain efficient and interpretable algorithms, we exploit the fact that the centroid w.r.t the squared Lorentzian distance can be written in closedform. We show that the Euclidean norm of such a centroid decreases as the curvature of the hyperbolic space decreases. This property makes it appropriate to represent hierarchies where parent nodes minimize the distances to their descendants and have smaller Euclidean norm than their children. Our approach obtains stateoftheart results in retrieval and classification tasks on different datasets.
Related Material


