Functional Connectivity Graph Neural Networks

Real-world networks often benefit from capturing both local and global interactions. Inspired by multi-modal analysis in brain imaging, where structural and functional connectivity offer complementary views of network organization, we propose a graph neural network framework that generalizes this ap...

Full description

Saved in:
Bibliographic Details
Main Authors Li, Yang, Yi, Luopeiwen, Songdechakraiwut, Tananun
Format Journal Article
LanguageEnglish
Published 07.08.2025
Subjects
Computer Science - Neural and Evolutionary Computing
Online AccessGet full text
DOI10.48550/arxiv.2508.05786

Cover

More Information
Summary:Real-world networks often benefit from capturing both local and global interactions. Inspired by multi-modal analysis in brain imaging, where structural and functional connectivity offer complementary views of network organization, we propose a graph neural network framework that generalizes this approach to other domains. Our method introduces a functional connectivity block based on persistent graph homology to capture global topological features. Combined with structural information, this forms a multi-modal architecture called Functional Connectivity Graph Neural Networks. Experiments show consistent performance gains over existing methods, demonstrating the value of brain-inspired representations for graph-level classification across diverse networks.
DOI:10.48550/arxiv.2508.05786