Long-Range Graph Wavelet Networks

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Guerranti, Filippo, Forte, Fabrizio, Geisler, Simon, Günnemann, Stephan
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909839186198528
author Guerranti, Filippo
Forte, Fabrizio
Geisler, Simon
Günnemann, Stephan
author_facet Guerranti, Filippo
Forte, Fabrizio
Geisler, Simon
Günnemann, Stephan
contents Modeling long-range interactions, the propagation of information across distant parts of a graph, is a central challenge in graph machine learning. Graph wavelets, inspired by multi-resolution signal processing, provide a principled way to capture both local and global structures. However, existing wavelet-based graph neural networks rely on finite-order polynomial approximations, which limit their receptive fields and hinder long-range propagation. We propose Long-Range Graph Wavelet Networks (LR-GWN), which decompose wavelet filters into complementary local and global components. Local aggregation is handled with efficient low-order polynomials, while long-range interactions are captured through a flexible spectral-domain parameterization. This hybrid design unifies short- and long-distance information flow within a principled wavelet framework. Experiments show that LR-GWN achieves state-of-the-art performance among wavelet-based methods on long-range benchmarks, while remaining competitive on short-range datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2509_06743
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Long-Range Graph Wavelet Networks
Guerranti, Filippo
Forte, Fabrizio
Geisler, Simon
Günnemann, Stephan
Machine Learning
Artificial Intelligence
Modeling long-range interactions, the propagation of information across distant parts of a graph, is a central challenge in graph machine learning. Graph wavelets, inspired by multi-resolution signal processing, provide a principled way to capture both local and global structures. However, existing wavelet-based graph neural networks rely on finite-order polynomial approximations, which limit their receptive fields and hinder long-range propagation. We propose Long-Range Graph Wavelet Networks (LR-GWN), which decompose wavelet filters into complementary local and global components. Local aggregation is handled with efficient low-order polynomials, while long-range interactions are captured through a flexible spectral-domain parameterization. This hybrid design unifies short- and long-distance information flow within a principled wavelet framework. Experiments show that LR-GWN achieves state-of-the-art performance among wavelet-based methods on long-range benchmarks, while remaining competitive on short-range datasets.
title Long-Range Graph Wavelet Networks
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2509.06743