Riemannian Multinomial Logistics Regression for SPD Neural Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Ziheng, Song, Yue, Liu, Gaowen, Kompella, Ramana Rao, Wu, Xiaojun, Sebe, Nicu
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929282785214464
author Chen, Ziheng
Song, Yue
Liu, Gaowen
Kompella, Ramana Rao
Wu, Xiaojun
Sebe, Nicu
author_facet Chen, Ziheng
Song, Yue
Liu, Gaowen
Kompella, Ramana Rao
Wu, Xiaojun
Sebe, Nicu
contents 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 an approximated space rather than intrinsic classifiers that accurately capture the geometry of SPD manifolds. Inspired by Hyperbolic Neural Networks (HNNs), we propose Riemannian Multinomial Logistics Regression (RMLR) for the classification layers in SPD networks. We introduce a unified framework for building Riemannian classifiers under the metrics pulled back from the Euclidean space, and showcase our framework under the parameterized Log-Euclidean Metric (LEM) and Log-Cholesky Metric (LCM). Besides, our framework offers a novel intrinsic explanation for the most popular LogEig classifier in existing SPD networks. The effectiveness of our method is demonstrated in three applications: radar recognition, human action recognition, and electroencephalography (EEG) classification. The code is available at https://github.com/GitZH-Chen/SPDMLR.git.
format Preprint
id arxiv_https___arxiv_org_abs_2305_11288
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Riemannian Multinomial Logistics Regression for SPD Neural Networks
Chen, Ziheng
Song, Yue
Liu, Gaowen
Kompella, Ramana Rao
Wu, Xiaojun
Sebe, Nicu
Machine Learning
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 an approximated space rather than intrinsic classifiers that accurately capture the geometry of SPD manifolds. Inspired by Hyperbolic Neural Networks (HNNs), we propose Riemannian Multinomial Logistics Regression (RMLR) for the classification layers in SPD networks. We introduce a unified framework for building Riemannian classifiers under the metrics pulled back from the Euclidean space, and showcase our framework under the parameterized Log-Euclidean Metric (LEM) and Log-Cholesky Metric (LCM). Besides, our framework offers a novel intrinsic explanation for the most popular LogEig classifier in existing SPD networks. The effectiveness of our method is demonstrated in three applications: radar recognition, human action recognition, and electroencephalography (EEG) classification. The code is available at https://github.com/GitZH-Chen/SPDMLR.git.
title Riemannian Multinomial Logistics Regression for SPD Neural Networks
topic Machine Learning
url https://arxiv.org/abs/2305.11288