When Brain Foundation Model Meets Cauchy-Schwarz Divergence: A New Framework for Cross-Subject Motor Imagery Decoding

TL;DR

This paper introduces a new cross-subject motor imagery EEG decoding framework that uses a pretrained Brain Foundation Model for source selection and Cauchy-Schwarz divergence for feature and decision alignment, improving accuracy and efficiency.

Contribution

It proposes a novel MSDA method leveraging a pretrained BFM for source selection and Cauchy-Schwarz divergence for alignment, addressing inter-subject variability and negative transfer issues.

Findings

Achieves average accuracies of 86.17% and 78.41% on two datasets.

Outperforms state-of-the-art methods in MI-EEG decoding.

Demonstrates scalability and efficiency with large source pools.

Abstract

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, cross-subject 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 achieves average accuracies of 86.17% and 78.41%, outperforming 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.