English

Functional Connectivity Graph Neural Networks

Neural and Evolutionary Computing 2025-08-11 v1

Abstract

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.

Keywords

Cite

@article{arxiv.2508.05786,
  title  = {Functional Connectivity Graph Neural Networks},
  author = {Yang Li and Luopeiwen Yi and Tananun Songdechakraiwut},
  journal= {arXiv preprint arXiv:2508.05786},
  year   = {2025}
}

Comments

26 pages, 5 figures, 24 tables

R2 v1 2026-07-01T04:39:52.184Z