When Brain Foundation Model Meets Cauchy-Schwarz Divergence: A New Framework for Cross-Subject Motor Imagery Decoding
This work addresses the challenge of inter-subject variability in brain-computer interfaces, offering a scalable solution for reducing calibration costs for new users, though it is incremental in improving existing domain adaptation methods.
The paper tackles the problem of cross-subject motor imagery EEG decoding by proposing a novel multi-source domain adaptation framework that uses a Brain Foundation Model for dynamic source selection and Cauchy-Schwarz divergences for alignment, achieving state-of-the-art performance on benchmark datasets with reduced training time.
Decoding motor imagery (MI) electroencephalogram (EEG) signals, a key non-invasive brain-computer interface (BCI) paradigm for controlling external systems, has been significantly advanced by deep learning. However, MI-EEG decoding remains challenging due to substantial inter-subject variability and limited labeled target data, which necessitate costly calibration for new users. Many existing multi-source domain adaptation (MSDA) methods indiscriminately incorporate all available source domains, disregarding the large inter-subject differences in EEG signals, which leads to negative transfer and excessive computational costs. Moreover, while many approaches focus on feature distribution alignment, they often neglect the explicit dependence between features and decision-level outputs, limiting their ability to preserve discriminative structures. To address these gaps, we propose a novel MSDA framework that leverages a pretrained large Brain Foundation Model (BFM) for dynamic and informed source subject selection, ensuring only relevant sources contribute to adaptation. Furthermore, we employ Cauchy-Schwarz (CS) and Conditional CS (CCS) divergences to jointly perform feature-level and decision-level alignment, enhancing domain invariance while maintaining class discriminability. Extensive evaluations on two benchmark MI-EEG datasets demonstrate that our framework outperforms a broad range of state-of-the-art baselines. Additional experiments with a large source pool validate the scalability and efficiency of BFM-guided selection, which significantly reduces training time without sacrificing performance.