Beyond Pairwise Connections: Extracting High-Order Functional Brain Network Structures under Global Constraints

2025-10-10

AI Summary

Traditional functional brain network (FBN) modeling relies on pairwise connectivity, failing to capture higher-order dependencies; existing hypergraph-based approaches suffer from high computational cost and heuristic design, hindering end-to-end learning. To address this, we propose a globally constrained, multi-resolution hypergraph learning framework that, for the first time, incorporates four interpretable constraints—signal synchrony, subject identity consistency, expected edge cardinality control, and task-label guidance—to enable direct, end-to-end learning of higher-order FBN topology from data distributions. Evaluated on five public datasets across two neuroimaging tasks, our method significantly outperforms nine baseline and ten state-of-the-art methods, achieving up to a 30.6% relative improvement in classification accuracy while reducing computational time by 96.3%. The framework ensures strong interpretability, computational efficiency, and cross-scale generalizability.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• Economics, Online Markets and Human Computation: Social networks and social learning

Abstract

Functional brain network (FBN) modeling often relies on local pairwise interactions, whose limitation in capturing high-order dependencies is theoretically analyzed in this paper. Meanwhile, the computational burden and heuristic nature of current hypergraph modeling approaches hinder end-to-end learning of FBN structures directly from data distributions. To address this, we propose to extract high-order FBN structures under global constraints, and implement this as a Global Constraints oriented Multi-resolution (GCM) FBN structure learning framework. It incorporates 4 types of global constraint (signal synchronization, subject identity, expected edge numbers, and data labels) to enable learning FBN structures for 4 distinct levels (sample/subject/group/project) of modeling resolution. Experimental results demonstrate that GCM achieves up to a 30.6% improvement in relative accuracy and a 96.3% reduction in computational time across 5 datasets and 2 task settings, compared to 9 baselines and 10 state-of-the-art methods. Extensive experiments validate the contributions of individual components and highlight the interpretability of GCM. This work offers a novel perspective on FBN structure learning and provides a foundation for interdisciplinary applications in cognitive neuroscience. Code is publicly available on https://github.com/lzhan94swu/GCM.

Problem

• Capturing high-order dependencies in functional brain networks
• Reducing computational burden of hypergraph modeling approaches
• Learning brain network structures under global constraints

Innovation

• Extracts high-order functional brain networks under global constraints
• Implements multi-resolution framework with four constraint types
• Achieves significant accuracy gains and computational efficiency improvements