Mutual-Guided Expert Collaboration for Cross-Subject EEG Classification

TL;DR

This paper introduces MGEC, a novel framework for EEG classification that balances domain-specific and domain-invariant features through expert collaboration, improving generalization across subjects.

Contribution

The paper presents a theoretically grounded, expert-guided neural network architecture that effectively models both reducible and irreducible domain-specific functions in EEG data.

Findings

MGEC outperforms existing methods on seven benchmarks.

Theoretical analysis links model reducibility to domain generalization.

Shared and routed expert modules effectively capture different feature types.

Abstract

Decoding the human brain from electroencephalography (EEG) signals holds promise for understanding neurological activities. However, EEG data exhibit heterogeneity across subjects and sessions, limiting the generalization of existing methods. Representation learning approaches sacrifice subject-specific information for domain invariance, while ensemble learning methods risk error accumulation for unseen subjects. From a theoretical perspective, we reveal that the applicability of these paradigms depends on the reducibility cost of domain-specific functions to domain-invariant ones. Building on this insight, we propose a Mutual-Guided Expert Collaboration (MGEC) framework that employs distinct network structures aligned with domain-specific and domain-invariant functions. Shared expert-guided learning captures reducible domain-invariant functions. Routed expert-guided learning employs a mixture-of-experts architecture to model irreducible domain-specific functions. Mutual-guided learning enables collaborative regularization to prevent over-reduction and under-reduction. We validate our theoretical findings on synthetic datasets, and experiments on seven benchmarks demonstrate that MGEC outperforms state-of-the-art methods.