# Learning Structural-Functional Brain Representations through Multi-Scale Adaptive Graph Attention for Cognitive Insight

arXiv: https://arxiv.org/abs/2603.29967 · HTML: https://mlsanity.com/paper/2603.29967/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 20 references that are in the map.
- First posted on arXiv 31 Mar 2026.

## Builds on (most cited first, 9 of 9)

- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [A Generalization of Transformer Networks to Graphs](https://mlsanity.com/paper/2012.09699/) (2020)
- [Joint Embedding of Structural and Functional Brain Networks with Graph Neural Networks for Mental Illness Diagnosis](https://mlsanity.com/paper/2107.03220/) (2021)
- [Brain Networks and Intelligence: A Graph Neural Network Based Approach to Resting State fMRI Data](https://mlsanity.com/paper/2311.03520/) (2023)
- [Joint Graph Convolution for Analyzing Brain Structural and Functional Connectome](https://mlsanity.com/paper/2211.07363/) (2022)
- [Physics-Guided Multi-View Graph Neural Network for Schizophrenia Classification via Structural-Functional Coupling](https://mlsanity.com/paper/2505.15135/) (2025)
- [Unified Cross-Modal Attention-Mixer Based Structural-Functional Connectomics Fusion for Neuropsychiatric Disorder Diagnosis](https://mlsanity.com/paper/2505.15139/) (2025)
- [NeuroKoop: Neural Koopman Fusion of Structural-Functional Connectomes for Identifying Prenatal Drug Exposure in Adolescents](https://mlsanity.com/paper/2508.16414/) (2025)
- [KOCOBrain: Kuramoto-Guided Graph Network for Uncovering Structure-Function Coupling in Adolescent Prenatal Drug Exposure](https://mlsanity.com/paper/2601.11018/) (2026)

## Abstract (arXiv)

Understanding how brain structure and function interact is key to explaining intelligence yet modeling them jointly is challenging as the structural and functional connectome capture complementary aspects of organization. We introduced Multi-scale Adaptive Graph Network (MAGNet), a Transformer-style graph neural network framework that adaptively learns structure-function interactions. MAGNet leverages source-based morphometry from structural MRI to extract inter-regional morphological features and fuses them with functional network connectivity from resting-state fMRI. A hybrid graph integrates direct and indirect pathways, while local-global attention refines connectivity importance and a joint loss simultaneously enforces cross-modal coherence and optimizes the prediction objective end-to-end. On the ABCD dataset, MAGNet outperformed relevant baselines, demonstrating effective multimodal integration for advancing our understanding of cognitive function.