cs.LGNov 10, 2026

ScaleBrain: A Scale-Consistent Framework for EEG Foundation Models

Authors: Minyu Zhou, Yajing Wu, Yongqiang Tang, Wang Jia, Wensheng Zhang

Organizations: College of Computer Science, Nankai University, Tianjin 300350, China · State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China · Department of Neurosurgery, Beijing Tiantan Hospital, Capital Medical University, Beijing 100070, China · School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou 510006, China

Abstract

Foundation models pre-trained on large unlabeled electroencephalography (EEG) corpora have emerged as a transformative paradigm for Brain-Computer Interface (BCI) applications. Recent EEG foundation models have shown that multi-scale representations derived from fixed-length patches can improve EEG representation learning. Existing frameworks commonly construct temporal scales through feature-level operations. However, these operations leave the correspondence between learned features and scale-specific characteristics of the original EEG signals implicit. Moreover, when the self-supervised objective is not aligned with the multi-scale input representations, information at some temporal scales may receive insufficient supervision during pre-training. In light of this, we propose ScaleBrain, a scale-consistent pre-training framework that explicitly coordinates multi-scale representations of EEG from both the model input and optimization objective sides. Specifically, ScaleBrain introduces multi-scale EEG tokenization to represent the same EEG segment through analysis windows with different temporal spans and shared temporal anchors, and pairs these representations with scale-specific reconstruction to align with the multi-scale input structure and provide supervision across temporal resolutions during self-supervised learning. We further develop an axial spatio-temporal attention mechanism to contextualize the fused multi-scale representation along spatial and temporal dimensions. Extensive evaluations on six public BCI benchmarks against 12 representative baselines show that ScaleBrain achieves the highest mean Balanced Accuracy on five datasets and ranks third on the remaining one, with only 5.0M parameters, demonstrating strong performance and favorable parameter efficiency.

Figures & tables

Explore similar work

CardsList
  1. BrainCodes: A Lightweight EEG Foundation Model over Discrete Neural Codes

    Oct 21, 2026Kleanthis Avramidis, Ivan Tashev, Dimitra EmmanouilidouEEG Foundation ModelsRepresentation Learning

  2. LaBraM at Scale: Scaling Data and Models for EEG Pretraining

    Nov 2, 2026Jun-Yu Pan, Ruicheng Yin, Bao-Liang Lu +3EEG Foundation ModelsSelf-Supervised Pre-Training