Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Bellante, Armando, Plávala, Martin, Luongo, Alessandro
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2505.23609
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915312672178176
author Bellante, Armando
Plávala, Martin
Luongo, Alessandro
author_facet Bellante, Armando
Plávala, Martin
Luongo, Alessandro
contents This paper proposes a family of permutation-invariant graph embeddings, generalizing the Skew Spectrum of graphs of Kondor & Borgwardt (2008). Grounded in group theory and harmonic analysis, our method introduces a new class of graph invariants that are isomorphism-invariant and capable of embedding richer graph structures - including attributed graphs, multilayer graphs, and hypergraphs - which the Skew Spectrum could not handle. Our generalization further defines a family of functions that enables a trade-off between computational complexity and expressivity. By applying generalization-preserving heuristics to this family, we improve the Skew Spectrum's expressivity at the same computational cost. We formally prove the invariance of our generalization, demonstrate its improved expressiveness through experiments, and discuss its efficient computation.
format Preprint
id arxiv_https___arxiv_org_abs_2505_23609
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle The Generalized Skew Spectrum of Graphs
Bellante, Armando
Plávala, Martin
Luongo, Alessandro
Machine Learning
Data Structures and Algorithms
Group Theory
Representation Theory
This paper proposes a family of permutation-invariant graph embeddings, generalizing the Skew Spectrum of graphs of Kondor & Borgwardt (2008). Grounded in group theory and harmonic analysis, our method introduces a new class of graph invariants that are isomorphism-invariant and capable of embedding richer graph structures - including attributed graphs, multilayer graphs, and hypergraphs - which the Skew Spectrum could not handle. Our generalization further defines a family of functions that enables a trade-off between computational complexity and expressivity. By applying generalization-preserving heuristics to this family, we improve the Skew Spectrum's expressivity at the same computational cost. We formally prove the invariance of our generalization, demonstrate its improved expressiveness through experiments, and discuss its efficient computation.
title The Generalized Skew Spectrum of Graphs
topic Machine Learning
Data Structures and Algorithms
Group Theory
Representation Theory
url https://arxiv.org/abs/2505.23609