Riemannian Multiclass Logistics Regression for SPD Neural Networks

05/18/2023
by   Ziheng Chen, et al.
0

Deep neural networks for learning symmetric positive definite (SPD) matrices are gaining increasing attention in machine learning. Despite the significant progress, most existing SPD networks use traditional Euclidean classifiers on approximated spaces rather than intrinsic classifiers that accurately capture the geometry of SPD manifolds. Inspired by the success of hyperbolic neural networks (HNNs), we propose Riemannian multiclass logistics regression (RMLR) for SPD networks. We introduce a general unified framework for a family of Riemannian metrics on SPD manifolds and showcase the specific n-invariant Log-Euclidean Metrics for SPD networks. Moreover, we encompass the most popular classifier in existing SPD networks as a special case of our framework. Extensive experiments on popular SPD learning benchmarks demonstrate the superiority of our classifiers.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/26/2023

Adaptive Riemannian Metrics on SPD Manifolds

Symmetric Positive Definite (SPD) matrices have received wide attention ...
research
05/08/2023

Building Neural Networks on Matrix Manifolds: A Gyrovector Space Approach

Matrix manifolds, such as manifolds of Symmetric Positive Definite (SPD)...
research
05/21/2018

geomstats: a Python Package for Riemannian Geometry in Machine Learning

We introduce geomstats, a python package that performs computations on m...
research
05/11/2020

Design and visualization of Riemannian metrics

Local and global illumination were recently defined in Riemannian manifo...
research
12/21/2021

Dynamically Stable Poincaré Embeddings for Neural Manifolds

In a Riemannian manifold, the Ricci flow is a partial differential equat...
research
06/30/2020

Graph Laplacians, Riemannian Manifolds and their Machine-Learning

Graph Laplacians as well as related spectral inequalities and (co-)homol...
research
06/05/2023

R-Mixup: Riemannian Mixup for Biological Networks

Biological networks are commonly used in biomedical and healthcare domai...

Please sign up or login with your details

Forgot password? Click here to reset