Building Neural Networks on Matrix Manifolds: A Gyrovector Space Approach

by   Xuan Son NGuyen, et al.

Matrix manifolds, such as manifolds of Symmetric Positive Definite (SPD) matrices and Grassmann manifolds, appear in many applications. Recently, by applying the theory of gyrogroups and gyrovector spaces that is a powerful framework for studying hyperbolic geometry, some works have attempted to build principled generalizations of Euclidean neural networks on matrix manifolds. However, due to the lack of many concepts in gyrovector spaces for the considered manifolds, e.g., the inner product and gyroangles, techniques and mathematical tools provided by these works are still limited compared to those developed for studying hyperbolic geometry. In this paper, we generalize some notions in gyrovector spaces for SPD and Grassmann manifolds, and propose new models and layers for building neural networks on these manifolds. We show the effectiveness of our approach in two applications, i.e., human action recognition and knowledge graph completion.


page 1

page 2

page 3

page 4


Riemannian Multiclass Logistics Regression for SPD Neural Networks

Deep neural networks for learning symmetric positive definite (SPD) matr...

Switch Spaces: Learning Product Spaces with Sparse Gating

Learning embedding spaces of suitable geometry is critical for represent...

Building Deep Networks on Grassmann Manifolds

Learning representations on Grassmann manifolds is popular in quite a fe...

Sparsifying networks by traversing Geodesics

The geometry of weight spaces and functional manifolds of neural network...

Geometric integration on symmetric spaces

We consider geometric numerical integration algorithms for differential ...

Computing complete hyperbolic structures on cusped 3-manifolds

A fundamental way to study 3-manifolds is through the geometric lens, on...

Kahler toric manifolds from dually flat spaces

We present a correspondence between real analytic Kähler toric manifolds...

Please sign up or login with your details

Forgot password? Click here to reset