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

• URL: http://arxiv.org/abs/2603.29967v1
• Date: Tue, 31 Mar 2026 16:32:15 GMT
• Title: Learning Structural-Functional Brain Representations through Multi-Scale Adaptive Graph Attention for Cognitive Insight
• Abstract summary: We introduce Multi-scale Adaptive Graph Network (MAGNet), a graph neural network framework that adaptively learns structure-function interactions.<n>A hybrid graph integrates direct and indirect pathways, while local-global attention refines connectivity importance and a joint loss enforces cross-modal coherence.<n>On the ABCD dataset, MAGNet outperformed relevant baselines, demonstrating effective multimodal integration for advancing our understanding of cognitive function.
• Score: 15.13186621391124
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Brain Network Classification Based on Graph Contrastive Learning and Graph Transformer [0.6906005491572401]
  This paper proposes a novel model named PHGCL-DDGformer that integrates graph contrastive learning with graph transformers.<n> Experimental results on real-world datasets demonstrate that the PHGCL-DDGformer model outperforms existing state-of-the-art approaches in brain network classification tasks.
  arXiv  Detail & Related papers  (2025-04-01T13:26:03Z)
• Online Multi-modal Root Cause Analysis [61.94987309148539]
  Root Cause Analysis (RCA) is essential for pinpointing the root causes of failures in microservice systems. Existing online RCA methods handle only single-modal data overlooking, complex interactions in multi-modal systems. We introduce OCEAN, a novel online multi-modal causal structure learning method for root cause localization.
  arXiv  Detail & Related papers  (2024-10-13T21:47:36Z)
• DGNN: Decoupled Graph Neural Networks with Structural Consistency between Attribute and Graph Embedding Representations [62.04558318166396]
  Graph neural networks (GNNs) demonstrate a robust capability for representation learning on graphs with complex structures. A novel GNNs framework, dubbed Decoupled Graph Neural Networks (DGNN), is introduced to obtain a more comprehensive embedding representation of nodes. Experimental results conducted on several graph benchmark datasets verify DGNN's superiority in node classification task.
  arXiv  Detail & Related papers  (2024-01-28T06:43:13Z)
• Brain Networks and Intelligence: A Graph Neural Network Based Approach to Resting State fMRI Data [2.193937336601403]
  We present a novel modeling architecture called BrainRGIN for predicting intelligence (fluid, crystallized, and total intelligence) using graph neural networks on rsfMRI derived connectivity matrices. Our approach incorporates a clustering-based embedding and graph isomorphism network in the graph convolutional layer to reflect the nature of the brain sub-network organization.
  arXiv  Detail & Related papers  (2023-11-06T20:58:07Z)
• Language Knowledge-Assisted Representation Learning for Skeleton-Based Action Recognition [71.35205097460124]
  How humans understand and recognize the actions of others is a complex neuroscientific problem. LA-GCN proposes a graph convolution network using large-scale language models (LLM) knowledge assistance.
  arXiv  Detail & Related papers  (2023-05-21T08:29:16Z)
• Joint Graph Convolution for Analyzing Brain Structural and Functional Connectome [11.016035878136034]
  We propose to couple the two networks of an individual by adding inter-network edges between corresponding brain regions. The weights of inter-network edges are learnable, reflecting non-uniform structure-function coupling strength across the brain. We apply our Joint-GCN to predict age and sex of 662 participants from the public dataset of the National Consortium on Alcohol and Neurodevelopment in Adolescence.
  arXiv  Detail & Related papers  (2022-10-27T23:43:34Z)
• Unified Embeddings of Structural and Functional Connectome via a Function-Constrained Structural Graph Variational Auto-Encoder [2.8719792727222364]
  We propose a function-constrained structural graph variational autoencoder capable of incorporating information from both functional and structural connectomes in an unsupervised fashion. This leads to a joint low-dimensional embedding that establishes a unified spatial coordinate system for comparing across different subjects.
  arXiv  Detail & Related papers  (2022-07-05T21:39:13Z)
• Functional2Structural: Cross-Modality Brain Networks Representation Learning [55.24969686433101]
  Graph mining on brain networks may facilitate the discovery of novel biomarkers for clinical phenotypes and neurodegenerative diseases. We propose a novel graph learning framework, known as Deep Signed Brain Networks (DSBN), with a signed graph encoder. We validate our framework on clinical phenotype and neurodegenerative disease prediction tasks using two independent, publicly available datasets.
  arXiv  Detail & Related papers  (2022-05-06T03:45:36Z)
• Learning to Model the Relationship Between Brain Structural and Functional Connectomes [16.096428756895918]
  We develop a graph representation learning framework to model the relationship between brainobjective connectivity (SC) and functional connectivity (FC) A trainable graph convolutional encoder captures interactions between brain regions-of-interest that mimic actual neural communications. Experiments demonstrate that the learnt representations capture valuable information from the intrinsic properties of the subject's brain networks.
  arXiv  Detail & Related papers  (2021-12-18T11:23:55Z)
• Learning Connectivity of Neural Networks from a Topological Perspective [80.35103711638548]
  We propose a topological perspective to represent a network into a complete graph for analysis. By assigning learnable parameters to the edges which reflect the magnitude of connections, the learning process can be performed in a differentiable manner. This learning process is compatible with existing networks and owns adaptability to larger search spaces and different tasks.
  arXiv  Detail & Related papers  (2020-08-19T04:53:31Z)
• Tensor Graph Convolutional Networks for Multi-relational and Robust Learning [74.05478502080658]
  This paper introduces a tensor-graph convolutional network (TGCN) for scalable semi-supervised learning (SSL) from data associated with a collection of graphs, that are represented by a tensor. The proposed architecture achieves markedly improved performance relative to standard GCNs, copes with state-of-the-art adversarial attacks, and leads to remarkable SSL performance over protein-to-protein interaction networks.
  arXiv  Detail & Related papers  (2020-03-15T02:33:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.