ScaleBrain improves EEG analysis with scale-consistent model training
ScaleBrain: A Scale-Consistent Framework for EEG Foundation Models
Machine Learning
Summary
Analyzing brain signals called EEG is tricky because those signals change at different speeds over time. The authors propose ScaleBrain, a new method that looks at these brain signals at multiple time scales simultaneously and trains the model to understand each scale clearly. This approach helps the model learn more precise brain signal patterns. Tested on six brain-computer interface tasks, ScaleBrain performed better than other leading methods while using fewer model parameters.
What this means in practice
- •For brain-computer interface developers: Enhance EEG signal interpretation in BCIs by integrating ScaleBrain's multi-scale training for improved recognition accuracy with fewer parameters.
- •For clinical neurotechnology teams: Develop more reliable EEG-based diagnostic tools by applying ScaleBrain to better capture temporal dynamics in brain signals.
Authors
Minyu Zhou, Yajing Wu, Yongqiang Tang, Wang Jia, Wensheng Zhang
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.