PTSM: Physiology-aware and Task-invariant Spatio-temporal Modeling for Cross-Subject EEG Decoding

TL;DR

This paper introduces PTSM, a novel EEG decoding framework that effectively captures both individual-specific and shared neural patterns, enabling robust cross-subject generalization without calibration.

Contribution

The paper proposes a physiology-aware, task-invariant spatio-temporal modeling approach with a dual-branch masking mechanism and disentanglement constraints for improved cross-subject EEG decoding.

Findings

Achieves strong zero-shot generalization on motor imagery datasets.

Outperforms state-of-the-art baselines without subject-specific calibration.

Demonstrates effective disentanglement of task-related and subject-related neural features.

Abstract

Cross-subject electroencephalography (EEG) decoding remains a fundamental challenge in brain-computer interface (BCI) research due to substantial inter-subject variability and the scarcity of subject-invariant representations. This paper proposed PTSM (Physiology-aware and Task-invariant Spatio-temporal Modeling), a novel framework for interpretable and robust EEG decoding across unseen subjects. PTSM employs a dual-branch masking mechanism that independently learns personalized and shared spatio-temporal patterns, enabling the model to preserve individual-specific neural characteristics while extracting task-relevant, population-shared features. The masks are factorized across temporal and spatial dimensions, allowing fine-grained modulation of dynamic EEG patterns with low computational overhead. To further address representational entanglement, PTSM enforces information-theoretic constraints that decompose latent embeddings into orthogonal task-related and subject-related subspaces. The model is trained end-to-end via a multi-objective loss integrating classification, contrastive, and disentanglement objectives. Extensive experiments on cross-subject motor imagery datasets demonstrate that PTSM achieves strong zero-shot generalization, outperforming state-of-the-art baselines without subject-specific calibration. Results highlight the efficacy of disentangled neural representations for achieving both personalized and transferable decoding in non-stationary neurophysiological settings.