{"ID":2885407,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.05786","arxiv_id":"2508.05786","title":"Functional Connectivity Graph Neural Networks","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.","short_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 doma...","url_abs":"https://arxiv.org/abs/2508.05786","url_pdf":"https://arxiv.org/pdf/2508.05786v1","authors":"[\"Yang Li\",\"Luopeiwen Yi\",\"Tananun Songdechakraiwut\"]","published":"2025-08-07T18:59:02Z","proceeding":"cs.NE","tasks":"[\"cs.NE\"]","methods":"[\"Graph Neural Network\",\"Generative Adversarial Network\"]","has_code":false}