用动态图模型分析脑电异常，能区分不同亚型且结果可解释。
Adaptive Multi-Expert Graph Transformer for Interpretable EEG-Based Diagnostics
- 将脑电信号建模为时序动态功能连接图，分层次编码电极到全局信息。
- 在TUAB数据集上达到先进检测性能，支持亚型感知的异常预测。
- 自适应专家融合机制提升可解释性，适合临床辅助诊断场景。
脑电图（EEG）异常源于空间与时间尺度上神经同步性的动态变化，但许多计算方法将其简化为静态特征。本文提出一种空间多专家图变压器，将每段EEG记录建模为动态功能连接图序列。通过加权相位滞后指数（wPLI）估算时变连接性，并采用分层图编码整合电极、区域及全局信息。多专家变压器架构实现亚型感知推理，门控机制自适应融合专家输出以进行全局异常预测。在TUAB数据集上的实验表明，该方法具备竞争力的异常检测性能，并展示了动态图建模与自适应专家融合在可解释、亚型感知的空间-时序分析中的潜力。
原文摘要 · Abstract (English)
Electroencephalographic (EEG) abnormalities arise from dynamic changes in neural synchrony across spatial and temporal scales, yet many computational approaches reduce these dynamics to static features. We present a Spatial Multi-Expert Graph Transformer that models each EEG recording as a sequence of dynamic functional connectivity graphs. Time-resolved connectivity is estimated using the weighted Phase Lag Index (wPLI), and hierarchical graph encoding aggregates information from electrode to regional and global levels. A multi-expert transformer architecture enables subtype-aware reasoning, with a gating mechanism adaptively fusing expert outputs for global abnormality prediction. Experiments on the TUAB dataset show competitive abnormal EEG detection performance and demonstrate the potential of dynamic graph modeling with adaptive expert fusion for interpretable, subtype-aware spatial--temporal analysis.
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。