Learning with Covariance Matrices: Principal Component Analysis Meets Learning with Graphs

Paper recorded by Signals 4 on 2026-09-09 in cs.LG. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-09 on arXiv · recorded by Signals 4 on 2026-09-10

Category: cs.LG · 机器学习 · first seen 2026-09-10

Abstract

This feature article provides an overview of the theoretical foundations for coVariance neural networks (VNNs), i.e., graph neural networks (GNNs) operating on covariance matrices as graphs. Covariance matrices are ubiquitous across domains, and hence, the deployment of GNNs often leverages graphs of pairwise statistical dependencies. Existing theoretical contributions on GNNs consider abstract gr

Read on arXiv →