arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2501.01100cs.LG
收藏

长程脑图 Transformer

Long-range Brain Graph Transformer

Dalian University of Technology(大连理工大学);Zhejiang Institute of Optoelectronics(浙江光电研究院);Zhejiang Normal University(浙江师范大学);RMIT University(皇家墨尔本理工大学)

Shuo Yu, Shan Jin, Ming Li, Tabinda Sarwar, Feng Xia

AI总结:

本文提出 ALTER 脑图 Transformer,利用有偏随机游走显式建模脑区间长程依赖并融合短程依赖,在 ABIDE 和 ADNI 的疾病诊断中优于多种图学习方法。

摘要:

理解大脑感兴趣区域(ROIs)之间的通信和信息处理高度依赖长程连接性,这种连接性在促进全脑多种功能性神经整合方面发挥着关键作用。然而,以往研究通常关注脑网络内的短程依赖,而忽视了长程依赖,限制了对全脑通信的整体性理解。为解决这一局限,我们提出了 Adaptive Long-range aware TransformER(ALTER),这是一种利用有偏随机游走来捕捉大脑 ROIs 之间长程依赖的脑图 transformer。具体而言,我们提出了一种新颖的长程感知策略,以显式捕捉大脑 ROIs 之间的长程依赖。通过引导游走者前往具有更高相关值的下一跳,该策略模拟了真实世界中的全脑通信。此外,通过采用 transformer 框架,ALTER 自适应地整合大脑 ROIs 之间的短程和长程依赖,从而实现对全脑多层次通信的整体性理解。在 ABIDE 和 ADNI 数据集上的大量实验表明,在神经系统疾病诊断中,ALTER 始终优于通用的最先进图学习方法(包括 SAN、Graphormer、GraphTrans 和 LRGNN)以及其他基于图学习的脑网络分析方法(包括 FBNETGEN、BrainNetGNN、BrainGNN 和 BrainNETTF)。文中还展示了长程依赖的案例,以进一步说明 ALTER 的有效性。实现代码可在 https://github.com/yushuowiki/ALTER 获取。

英文摘要:

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 https://github.com/yushuowiki/ALTER.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑