Power spectrum signatures of graphs

Yim, Ka Man ORCID: https://orcid.org/0000-0003-4736-3151 and Djima, Karamatou Yacoubou 2026. Power spectrum signatures of graphs. Applied and Computational Harmonic Analysis 85 , 101893. 10.1016/j.acha.2026.101893

PDF - Published Version Available under License Creative Commons Attribution. Download (11MB)

Abstract

Point signatures based on the Laplacian operators on graphs, point clouds, and manifolds have become popular tools in machine learning for graphs, clustering, and shape analysis. In this work, we propose a novel point signature, the power spectrum signature, a measure on R defined as the squared graph Fourier transform of a graph signal. Unlike eigenvectors of the Laplacian from which it is derived, the power spectrum signature is invariant under graph automorphisms. We show that the power spectrum signature is stable under perturbations of the input graph with respect to the Wasserstein metric. We focus on the signature applied to classes of indicator functions, and its applications to generating descriptive features for vertices of graphs. To demonstrate the practical value of our signature, we showcase several applications in characterizing geometry and symmetries in point cloud data, and graph regression problems.

Item Type:	Article
Date Type:	Publication
Status:	Published
Schools:	Schools > Mathematics
Additional Information:	License information from Publisher: LICENSE 1: URL: http://creativecommons.org/licenses/by/4.0/, Start Date: 2026-05-15
Publisher:	Elsevier
ISSN:	1063-5203
Date of First Compliant Deposit:	28 May 2026
Date of Acceptance:	13 May 2026
Last Modified:	05 Aug 2026 02:31
URI:	https://orca.cardiff.ac.uk/id/eprint/187254

Actions (repository staff only)

Edit Item