Long-range Brain Graph Transformer

2025-01-02

AI Summary

Existing brain functional network studies overemphasize short-range connections while neglecting long-range functional communication, thereby limiting our understanding of whole-brain coordination mechanisms. To address this, we propose a graph transformer specifically designed for brain functional networks—the first to jointly model both short- and long-range dependencies in brain graph learning. Our method introduces an adaptive long-range perception strategy that simulates high-correlation distant interactions via bias-aware random walks; further, it integrates dynamic adjacency modeling with a multi-scale graph attention mechanism. Evaluated on the ABIDE and ADNI datasets, our approach achieves significantly higher disease classification accuracy than 12 state-of-the-art models, including SAN, Graphormer, and BrainGNN. The implementation is publicly available.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Humans and AI: Brain-Sensing and Analysis
• Reasoning under Uncertainty: Graphical Models

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Understanding communication and information processing among brain regions of interest (ROIs) is highly dependent on long-range connectivity, which plays a crucial role in facilitating diverse functional neural integration across the entire brain. However, previous studies generally focused on the short-range dependencies within brain networks while neglecting the long-range dependencies, limiting an integrated understanding of brain-wide communication. To address this limitation, we propose Adaptive Long-range aware TransformER (ALTER), a brain graph transformer to capture long-range dependencies between brain ROIs utilizing biased random walk. Specifically, we present a novel long-range aware strategy to explicitly capture long-range dependencies between brain ROIs. By guiding the walker towards the next hop with higher correlation value, our strategy simulates the real-world brain-wide communication. Furthermore, by employing the transformer framework, ALERT adaptively integrates both short- and long-range dependencies between brain ROIs, enabling an integrated understanding of multi-level communication across the entire brain. Extensive experiments on ABIDE and ADNI datasets demonstrate that ALTER consistently outperforms generalized state-of-the-art graph learning methods (including SAN, Graphormer, GraphTrans, and LRGNN) and other graph learning based brain network analysis methods (including FBNETGEN, BrainNetGNN, BrainGNN, and BrainNETTF) in neurological disease diagnosis. Cases of long-range dependencies are also presented to further illustrate the effectiveness of ALTER. The implementation is available at url{https://github.com/yushuowiki/ALTER}.

Problem

• Long-distance connectivity
• Brain communication
• Cortical coordination

Innovation

• ALTER
• long-distance connectivity
• brain network analysis