Year: 2026
Type: preprint
Abstract: Electroencephalography (EEG) data plays an important role in understanding human brain activity, with various major applications. While current approaches, which largely build on EEG foundation models, have demonstrated strong performance across datasets and tasks, they typically rely on a fixed temporal scale. This design choice limits their ability to capture characteristics of neural dynamic behavior, often spanning across multiple timescales, which are naturally captured in EEG recordings. To address this limitation, we propose MAGE (\textbf{Multi-timescale Adaptive Generalization for EEG}), a foundation model that dynamically adapts to capture and integrate information across different timescales. Specifically, MAGE combines two key mechanisms: (i) a novel multi-timescale attention mechanism, capable of learning representations across multiple temporal scales and (ii) a trainable aggregation module, that dynamically identifies and adapts to the most informative timescale of the input signal. Experimental results across seven datasets demonstrate that MAGE consistently outperforms existing EEG foundation models while using substantially fewer parameters. Moreover, our results support the hypothesis that different downstream tasks benefit from distinct temporal scales. All source code will be released.
Source: arXiv (Cornell University)
Institutions: Télécom Paris, Institut Polytechnique de Paris, Laboratoire Traitement et Communication de l’Information, Université de Technologie de Troyes, German Research Centre for Artificial Intelligence, Trường Đại học Khoa học và Công nghệ Hà Nội, Viện Nghiên cứu và Ứng dụng Trí tuệ nhân tạo, Hanoi University of Science and Technology
Language: English
Subfield: Cognitive Neuroscience
Field: Neuroscience
Domain: Life Sciences
Open Access status: green
OpenAlex ID: W7225756127