cs.LGSep 25, 2026

MAGE: Towards Generalizable Multi-timescale EEG Representations

Authors: Tuan-Kiet Doan, Van-Chien Nguyen, Trung-Hieu Tran, Quang-Hung Pham, Ngoc-Son Vu, Huy Phan, Phi Le Nguyen, Duc-Han Le, 

Organizations: LTCI, Télécom Paris, Institut Polytechnique de Paris, Palaiseau, France · LIST3N, Université de Technologie de Troyes · German Research Center for Artificial Intelligence (DFKI), Germany · Institute for AI Innovation and Societal Impact, Hanoi University of Science and Technology, Vietnam

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 (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.

Figures & tables

Appendix figures & tables13 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. ScaleBrain: A Scale-Consistent Framework for EEG Foundation Models

    Nov 10, 2026Minyu Zhou, Yajing Wu, Yongqiang Tang +2Axial AttentionEEG Foundation Models

  2. DSAINet: An Efficient Dual-Scale Attentive Interaction Network for General EEG Decoding

    Apr 20, 2026Zhiyuan Ma, Zeyuan Li, Zihao Qiu +6Cross-Subject EEG DecodingEEG Decoding