Electroencephalography (EEG) has emerged as a powerful tool for modeling human brain states. However, the widespread adoption of EEG-based recognition systems is hindered by low signal-to-noise ratios and the scarcity of labeled data. While existing studies often tackle these challenges in isolation, we propose a novel Cross-Device Representation Consistency (CDRC) pretraining paradigm that addresses both issues simultaneously. CDRC leverages self-supervised signals derived from representation distances and is trained through contrastive estimation. Specifically, our approach employs a transformer based dual-branch single-view embedding prediction task, combining with a contrastive feature alignment module to extract robust and discriminative representations. We first evaluate the CDRC model on a low signal-to-noise ratio emotion classification task involving wearable dry electrodes. Furthermore, we extend CDRC to a multimodal fusion setting to address a cross-device vigilance regression task involving heterogeneous physiological modalities. Extensive experiments on the PaDWEED and SEED-VIG datasets demonstrate that CDRC achieves performance comparable to fully supervised methods and reaches the stat-of-the-art results of existing self-supervised methods, setting a new benchmark in this field. Notably, its strong performance on subject-independent tasks highlights its effectiveness in mitigating subject variability. These results underscore the potential of CDRC to significantly enhance the practicality and scalability of EEG-based recognition systems, marking a meaningful step toward real-world brain-computer interfaces.
Zhang et al. (Mon,) studied this question.