Core-Periphery Principle Guided State Space Model for Functional Connectome Classification

2025-03-18

AI Summary

To address the dual bottlenecks in functional connectome classification—limited modeling capacity of conventional models and high computational complexity (O(n²)) of Transformer-based approaches—this paper proposes a structural-aware lightweight state space model. Our method explicitly incorporates the neuroscientifically grounded core-periphery (CP) network organization prior into the modeling framework, designing a CP-guided Mixture-of-Experts (CP-MoE) architecture synergistically integrated with the selective state space model (Mamba). Additionally, we introduce graph-structure-guided fMRI feature encoding to preserve topological constraints. Evaluated on the ABIDE and ADNI datasets, our approach achieves higher classification accuracy than state-of-the-art Transformers, while accelerating inference by 3.2× and reducing FLOPs by 67%. These improvements significantly enhance both diagnostic accuracy and computational efficiency for brain disorder identification.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Mixture of Experts (MoE)
• Computer Vision: Multi-modal Vision

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Understanding the organization of human brain networks has become a central focus in neuroscience, particularly in the study of functional connectivity, which plays a crucial role in diagnosing neurological disorders. Advances in functional magnetic resonance imaging and machine learning techniques have significantly improved brain network analysis. However, traditional machine learning approaches struggle to capture the complex relationships between brain regions, while deep learning methods, particularly Transformer-based models, face computational challenges due to their quadratic complexity in long-sequence modeling. To address these limitations, we propose a Core-Periphery State-Space Model (CP-SSM), an innovative framework for functional connectome classification. Specifically, we introduce Mamba, a selective state-space model with linear complexity, to effectively capture long-range dependencies in functional brain networks. Furthermore, inspired by the core-periphery (CP) organization, a fundamental characteristic of brain networks that enhances efficient information transmission, we design CP-MoE, a CP-guided Mixture-of-Experts that improves the representation learning of brain connectivity patterns. We evaluate CP-SSM on two benchmark fMRI datasets: ABIDE and ADNI. Experimental results demonstrate that CP-SSM surpasses Transformer-based models in classification performance while significantly reducing computational complexity. These findings highlight the effectiveness and efficiency of CP-SSM in modeling brain functional connectivity, offering a promising direction for neuroimaging-based neurological disease diagnosis.

Problem

• Improves classification of functional brain connectomes.
• Reduces computational complexity in brain network analysis.
• Enhances modeling of long-range dependencies in brain networks.

Innovation

• Core-Periphery State-Space Model (CP-SSM) for brain networks
• Mamba: linear complexity state-space model
• CP-MoE: Core-Periphery guided Mixture-of-Experts