发表机构
Shenzhen University; Guangdong Provincial Key Laboratory of Biomedical Measurements and Ultrasound Imaging（深圳大学; 广东省生物医学测量与超声成像重点实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对长时程脑电序列建模，提出基于微状态的脑令牌分词及多尺度交互模块，在五个数据集上优于现有模型，实现鲁棒可解释的脑电表示。
AI 中文摘要
脑电图（EEG）提供了观察动态大脑活动的非侵入性窗口，然而，由于脑电序列具有高时间复杂性、跨受试者显著变异性以及缺乏生物学意义的序列表示，对长时程脑电序列进行建模仍然具有挑战性。现有的分词策略，如固定窗口和基于分块的表示，根据人为的时间边界将脑电信号离散化，这可能会破坏内在的大脑状态动态。在这项工作中，我们提出了脑令牌学习（Brain-Token Learning），一种受神经科学启发的框架，引入了脑分词（Brain Tokenization）用于长时程脑电序列建模。脑分词不是将脑电信号划分为预定义的时间段，而是将脑电表示为循环微状态衍生的脑令牌序列，其中每个令牌对应于一个具有可变时间持续时间的准稳定大规模脑状态。基于这些生物学基础的令牌，我们进一步开发了一个多尺度令牌交互模块，包括潜在状态聚合（Latent State Aggregation）和状态转换建模（State Transition Modeling），以共同捕获全局脑状态上下文和局部微状态转换。我们在五个异构脑电数据集上评估了脑令牌（Brain-Token），包括新收集的长时程NeuroLong数据集和四个情感或临床脑电数据集（SEED、DEAP、MDD和NSSI）。大量实验表明，脑令牌在各种脑电场景中始终优于传统的CNN/LSTM架构、基于Transformer的模型和域适应方法。进一步的分析验证了基于微状态的分词和多尺度交互在学习鲁棒且可解释的脑电表示方面的有效性。这些结果确立了脑令牌作为长时程脑电序列建模的生物学基础分词范式。
英文摘要
Electroencephalography (EEG) provides a non-invasive window into dynamic brain activity, yet modeling long-horizon EEG sequences remains challenging due to their high temporal complexity, substantial variability across subjects, and the lack of biologically meaningful sequence representations. Existing tokenization strategies, such as fixed-window and patch-based representations, discretize EEG signals according to artificial temporal boundaries, which may disrupt intrinsic brain-state dynamics. In this work, we propose Brain-Token Learning, a neuroscience-inspired framework that introduces Brain Tokenization for long-horizon EEG sequence modeling. Instead of partitioning EEG signals into predefined temporal segments, Brain Tokenization represents EEG as sequences of recurrent microstate-derived brain tokens, where each token corresponds to a quasi-stable large-scale brain state with variable temporal duration. Based on these biologically grounded tokens, we further develop a multi-scale token interaction module consisting of Latent State Aggregation and State Transition Modeling to jointly capture global brain-state context and local microstate transitions. We evaluate Brain-Token on five heterogeneous EEG datasets, including the newly collected long-horizon NeuroLong dataset and four affective or clinical EEG datasets (SEED, DEAP, MDD, and NSSI). Extensive experiments demonstrate that Brain-Token consistently outperforms conventional CNN/LSTM architectures, Transformer-based models, and domain adaptation methods across diverse EEG scenarios. Further analysis verifies the effectiveness of microstate-based tokenization and multi-scale interaction for learning robust and interpretable EEG representations. These results establish Brain-Token as a biologically grounded tokenization paradigm for long-horizon EEG sequence modeling.
