Saved in:
Bibliographic Details
Main Authors: Vasileiou, Antonis, Cervino, Juan, Frossard, Pascal, Kanatsoulis, Charilaos I., Morris, Christopher, Schaub, Michael T., Vandergheynst, Pierre, Wang, Zhiyang, Wolf, Guy, Levie, Ron
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.10031
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908826535460864
author Vasileiou, Antonis
Cervino, Juan
Frossard, Pascal
Kanatsoulis, Charilaos I.
Morris, Christopher
Schaub, Michael T.
Vandergheynst, Pierre
Wang, Zhiyang
Wolf, Guy
Levie, Ron
author_facet Vasileiou, Antonis
Cervino, Juan
Frossard, Pascal
Kanatsoulis, Charilaos I.
Morris, Christopher
Schaub, Michael T.
Vandergheynst, Pierre
Wang, Zhiyang
Wolf, Guy
Levie, Ron
contents Graph neural networks (GNNs) are commonly divided into message-passing neural networks (MPNNs) and spectral graph neural networks, reflecting two largely separate research traditions in machine learning and signal processing. This paper argues that this divide is mostly artificial, hindering progress in the field. We propose a viewpoint in which both MPNNs and spectral GNNs are understood as different parametrizations of permutation-equivariant operators acting on graph signals. From this perspective, many popular architectures are equivalent in expressive power, while genuine gaps arise only in specific regimes. We further argue that MPNNs and spectral GNNs offer complementary strengths. That is, MPNNs provide a natural language for discrete structure and expressivity analysis using tools from logic and graph isomorphism research, while the spectral perspective provides principled tools for understanding smoothing, bottlenecks, stability, and community structure. Overall, we posit that progress in graph learning will be accelerated by clearly understanding the key similarities and differences between these two types of GNNs, and by working towards unifying these perspectives within a common theoretical and conceptual framework rather than treating them as competing paradigms.
format Preprint
id arxiv_https___arxiv_org_abs_2602_10031
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Position: Message-passing and spectral GNNs are two sides of the same coin
Vasileiou, Antonis
Cervino, Juan
Frossard, Pascal
Kanatsoulis, Charilaos I.
Morris, Christopher
Schaub, Michael T.
Vandergheynst, Pierre
Wang, Zhiyang
Wolf, Guy
Levie, Ron
Machine Learning
Graph neural networks (GNNs) are commonly divided into message-passing neural networks (MPNNs) and spectral graph neural networks, reflecting two largely separate research traditions in machine learning and signal processing. This paper argues that this divide is mostly artificial, hindering progress in the field. We propose a viewpoint in which both MPNNs and spectral GNNs are understood as different parametrizations of permutation-equivariant operators acting on graph signals. From this perspective, many popular architectures are equivalent in expressive power, while genuine gaps arise only in specific regimes. We further argue that MPNNs and spectral GNNs offer complementary strengths. That is, MPNNs provide a natural language for discrete structure and expressivity analysis using tools from logic and graph isomorphism research, while the spectral perspective provides principled tools for understanding smoothing, bottlenecks, stability, and community structure. Overall, we posit that progress in graph learning will be accelerated by clearly understanding the key similarities and differences between these two types of GNNs, and by working towards unifying these perspectives within a common theoretical and conceptual framework rather than treating them as competing paradigms.
title Position: Message-passing and spectral GNNs are two sides of the same coin
topic Machine Learning
url https://arxiv.org/abs/2602.10031