Evolvable Graph Diffusion Optimal Transport with Pattern-Specific Alignment for Brain Connectome Modeling

2025-09-16

AI Summary

Existing studies treat structural connectivity (SC) as a static topological scaffold for functional connectivity (FC), overlooking higher-order dependencies, nonlinear couplings, and spatial heterogeneity between SC and FC—leading to geometric misalignment. To address this, we propose an evolvable graph diffusion model to dynamically capture higher-order regional dependencies; design an optimal transport–based, pattern-specific alignment mechanism for geometry-aware SC–FC integration; and incorporate a Kolmogorov–Arnold network to model nonlinear interregional interactions. Evaluated on the REST-meta-MDD and ADNI datasets, our method significantly outperforms state-of-the-art approaches, enabling precise identification of disease-specific subnetworks in major depressive disorder and Alzheimer’s disease, and improving diagnostic classification accuracy. The framework establishes a novel paradigm for dissecting SC–FC mismatch mechanisms through principled, biologically grounded integration.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Web Mining and Content Analysis: Models for Web evolution
• Social Networks and Social Media: Computational social science

Abstract

Network analysis of human brain connectivity indicates that individual differences in cognitive abilities arise from neurobiological mechanisms inherent in structural and functional brain networks. Existing studies routinely treat structural connectivity (SC) as optimal or fixed topological scaffolds for functional connectivity (FC), often overlooking higher-order dependencies between brain regions and limiting the modeling of complex cognitive processes. Besides, the distinct spatial organizations of SC and FC complicate direct integration, as naive alignment may distort intrinsic nonlinear patterns of brain connectivity. In this study, we propose a novel framework called Evolvable Graph Diffusion Optimal Transport with Pattern-Specific Alignment (EDT-PA), designed to identify disease-specific connectome patterns and classify brain disorders. To accurately model high-order structural dependencies, EDT-PA incorporates a spectrum of evolvable modeling blocks to dynamically capture high-order dependencies across brain regions. Additionally, a Pattern-Specific Alignment mechanism employs optimal transport to align structural and functional representations in a geometry-aware manner. By incorporating a Kolmogorov-Arnold network for flexible node aggregation, EDT-PA is capable of modeling complex nonlinear interactions among brain regions for downstream classification. Extensive evaluations on the REST-meta-MDD and ADNI datasets demonstrate that EDT-PA outperforms state-of-the-art methods, offering a more effective framework for revealing structure-function misalignments and disorder-specific subnetworks in brain disorders. The project of this work is released via this link.

Problem

• Modeling complex brain connectivity patterns between structural and functional networks
• Aligning structural and functional brain representations without distorting intrinsic patterns
• Identifying disease-specific connectome patterns for accurate brain disorder classification

Innovation

• Evolvable graph diffusion captures high-order dependencies
• Pattern-specific alignment uses optimal transport for integration
• Kolmogorov-Arnold network models nonlinear interactions for classification