Brain-MGF: Multimodal Graph Fusion Network for EEG-fMRI Brain Connectivity Analysis Under Psilocybin
Sin-Yee Yap, Fuad Noman, Junn Yong Loo, Devon Stoliker, Moein Khajehnejad, Raphaël C. -w. Phan, David L. Dowe, Adeel Razi, Chee-Ming Ting
arXiv (Cornell University) November 23, 2025 preprint DOI: 10.48550/arxiv.2511.18325 (opens in new tab)
Study at a glance
AI-extracted from the abstract| Characteristics | Observational study |
|---|---|
| Population | Participants in the PsiConnect dataset |
| Intervention | Psilocybin |
| Topics | Psilocybin |
| Keywords | Graph Fusion Pattern recognition psychology Artificial neural network Encode Softmax function Artificial intelligence Node physics Interpretability Construct python library Machine learning |
| Key findings | Adaptive graph fusion of EEG and fMRI connectivity via Brain-MGF distinguishes psilocybin from no-psilocybin conditions with up to 76.0% accuracy and 85.8% ROC-AUC, outperforming unimodal and non-adaptive approaches. |
Abstract
Psychedelics, such as psilocybin, reorganise large-scale brain connectivity, yet how these changes are reflected across electrophysiological (electroencephalogram, EEG) and haemodynamic (functional magnetic resonance imaging, fMRI) networks remains unclear. We present Brain-MGF, a multimodal graph fusion network for joint EEG-fMRI connectivity analysis. For each modality, we construct graphs with partial-correlation edges and Pearson-profile node features, and learn subject-level embeddings via graph convolution. An adaptive softmax gate then fuses modalities with sample-specific weights to capture context-dependent contributions. Using the world's largest single-site psilocybin dataset, PsiConnect, Brain-MGF distinguishes psilocybin from no-psilocybin conditions in meditation and rest. Fusion improves over unimodal and non-adaptive variants, achieving 74.0% accuracy and 76.5% F1 score on meditation, and 76.0% accuracy with 85.8% ROC-AUC on rest. UMAP visualisations reveal clearer class separation for fused embeddings. These results indicate that adaptive graph fusion effectively integrates complementary EEG-fMRI information, providing an interpretable framework for characterising psilocybin-induced alterations in large-scale neural organisation.