用动态图增强脑电图的几何表示，提升解码精度
RepSPD: Enhancing SPD Manifold Representation in EEGs via Dynamic Graphs
- 在黎曼流形上用注意力机制融合功能连接信息
- 通过双向对齐策略减少曲率带来的几何失真
- 适合脑机接口与神经疾病诊断等临床场景
从脑电图（EEG）中解码大脑活动对神经科学和临床应用至关重要。近年来，基于几何深度学习（GDL）的方法因其在对称正定（SPD）流形上的理论基础而受到关注，能够以物理合理的方式揭示结构连通性。然而，现有基于SPD的方法主要聚焦于统计聚合，忽视了频段特异性同步及脑区局部拓扑结构。为此，我们提出RepSPD，一种新型的GDL模型。该模型在黎曼流形上引入交叉注意力机制，以图生成的功能连接特征调制SPD的几何属性。此外，我们设计全局双向对齐策略，重塑切空间嵌入，缓解由曲率引起的几何畸变，从而提升几何一致性。大量实验表明，所提框架显著优于现有EEG表示方法，在鲁棒性和泛化能力方面表现更优。
原文摘要 · Abstract (English)
Decoding brain activity from electroencephalography (EEG) is crucial for neuroscience and clinical applications. Among recent advances in deep learning for EEG, geometric learning stands out as its theoretical underpinnings on symmetric positive definite (SPD) allows revealing structural connectivity analysis in a physics-grounded manner. However, current SPD-based methods focus predominantly on statistical aggregation of EEGs, with frequency-specific synchronization and local topological structures of brain regions neglected. Given this, we propose RepSPD, a novel geometric deep learning (GDL)-based model. RepSPD implements a cross-attention mechanism on the Riemannian manifold to modulate the geometric attributes of SPD with graph-derived functional connectivity features. On top of this, we introduce a global bidirectional alignment strategy to reshape tangent-space embeddings, mitigating geometric distortions caused by curvature and thereby enhancing geometric consistency. Extensive experiments demonstrate that our proposed framework significantly outperforms existing EEG representation methods, exhibiting superior robustness and generalization capabilities.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。