SpecMoE：用于跨物种EEG解码的频谱混合专家基础模型
SpecMoE: Spectral Mixture-of-Experts Foundation Model for Cross-Species EEG Decoding
AI总结：
本文提出SpecMoE模型，通过改进的频谱掩码策略和混合专家框架，提升EEG信号解码性能，实现跨物种和跨受试者的高准确率。
摘要：
解码脑电图（EEG）信号中的神经活动协同是连接神经科学与人工智能的关键挑战。基础模型在通用EEG解码中取得进展，但现有框架在自监督预训练中主要依赖单独的时间和频谱掩码原始信号，这种策略往往偏向高频振荡，因为低频节律模式可通过未掩码信号轻易推断。我们引入了一个基础模型，利用一种新的高斯平滑掩码方案应用于短时傅里叶变换（STFT）地图。通过联合应用时间、频率和时间-频率高斯掩码，使重建任务更具挑战性，迫使模型学习高、低频域的复杂神经模式。为了在这一激进的掩码策略下有效恢复信号，我们设计了SpecHi-Net，一种U型分层架构，包含多个编码和解码阶段。为了加速大规模预训练，我们将数据分为三个子集，每个子集用于训练独立的专家模型。然后通过SpecMoE，一种由学习的频谱门控机制引导的混合专家框架，将这些模型组合起来。SpecMoE在多种EEG解码任务中实现了最先进的性能，包括睡眠分期、情绪识别、运动想象分类、异常信号检测和药物效应预测。重要的是，该模型在人类和小鼠EEG数据集上表现出强大的跨物种和跨受试者泛化能力，保持高准确率。
英文摘要：
Decoding the orchestration of neural activity in electroencephalography (EEG) signals is a central challenge in bridging neuroscience with artificial intelligence. Foundation models have made strides in generalized EEG decoding, yet many existing frameworks primarily relying on separate temporal and spectral masking of raw signals during self-supervised pretraining. Such strategies often tend to bias learning toward high-frequency oscillations, as low-frequency rhythmic patterns can be easily inferred from the unmasked signal. We introduce a foundation model that utilizes a novel Gaussian-smoothed masking scheme applied to short-time Fourier transform (STFT) maps. By jointly applying time, frequency, and time-frequency Gaussian masks, we make the reconstruction task much more challenging, forcing the model to learn intricate neural patterns across both high- and low-frequency domains. To effectively recover signals under this aggressive masking strategy, we design SpecHi-Net, a U-shaped hierarchical architecture with multiple encoding and decoding stages. To accelerate large-scale pretraining, we partition the data into three subsets, each used to train an independent expert model. We then combine these models through SpecMoE, a mixture of experts framework guided by a learned spectral gating mechanism. SpecMoE achieves state-of-the-art performance across a diverse set of EEG decoding tasks, including sleep staging, emotion recognition, motor imagery classification, abnormal signal detection, and drug effect prediction. Importantly, the model demonstrates strong cross-species and cross-subject generalization, maintaining high accuracy on both human and murine EEG datasets.
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。
