Complex-Weighted Convolutional Networks: Provable Expressiveness via Complex Diffusion

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Amado, Cristina López, Schwarz, Tassilo, Tian, Yu, Lambiotte, Renaud
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909909534113792
author Amado, Cristina López
Schwarz, Tassilo
Tian, Yu
Lambiotte, Renaud
author_facet Amado, Cristina López
Schwarz, Tassilo
Tian, Yu
Lambiotte, Renaud
contents Graph Neural Networks (GNNs) have achieved remarkable success across diverse applications, yet they remain limited by oversmoothing and poor performance on heterophilic graphs. To address these challenges, we introduce a novel framework that equips graphs with a complex-weighted structure, assigning each edge a complex number to drive a diffusion process that extends random walks into the complex domain. We prove that this diffusion is highly expressive: with appropriately chosen complex weights, any node-classification task can be solved in the steady state of a complex random walk. Building on this insight, we propose the Complex-Weighted Convolutional Network (CWCN), which learns suitable complex-weighted structures directly from data while enriching diffusion with learnable matrices and nonlinear activations. CWCN is simple to implement, requires no additional hyperparameters beyond those of standard GNNs, and achieves competitive performance on benchmark datasets. Our results demonstrate that complex-weighted diffusion provides a principled and general mechanism for enhancing GNN expressiveness, opening new avenues for models that are both theoretically grounded and practically effective.
format Preprint
id arxiv_https___arxiv_org_abs_2511_13937
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Complex-Weighted Convolutional Networks: Provable Expressiveness via Complex Diffusion
Amado, Cristina López
Schwarz, Tassilo
Tian, Yu
Lambiotte, Renaud
Machine Learning
Social and Information Networks
Dynamical Systems
Physics and Society
Graph Neural Networks (GNNs) have achieved remarkable success across diverse applications, yet they remain limited by oversmoothing and poor performance on heterophilic graphs. To address these challenges, we introduce a novel framework that equips graphs with a complex-weighted structure, assigning each edge a complex number to drive a diffusion process that extends random walks into the complex domain. We prove that this diffusion is highly expressive: with appropriately chosen complex weights, any node-classification task can be solved in the steady state of a complex random walk. Building on this insight, we propose the Complex-Weighted Convolutional Network (CWCN), which learns suitable complex-weighted structures directly from data while enriching diffusion with learnable matrices and nonlinear activations. CWCN is simple to implement, requires no additional hyperparameters beyond those of standard GNNs, and achieves competitive performance on benchmark datasets. Our results demonstrate that complex-weighted diffusion provides a principled and general mechanism for enhancing GNN expressiveness, opening new avenues for models that are both theoretically grounded and practically effective.
title Complex-Weighted Convolutional Networks: Provable Expressiveness via Complex Diffusion
topic Machine Learning
Social and Information Networks
Dynamical Systems
Physics and Society
url https://arxiv.org/abs/2511.13937