MMOC: Self-Supervised EEG Emotion Recognition Framework with Multi-Model Online Collaboration

TL;DR

This paper introduces MMOC, a self-supervised EEG emotion recognition framework with multi-model online collaboration, which adapts to unseen data and mitigates inter-subject variability for improved real-world performance.

Contribution

It proposes a novel multi-model online collaboration approach that dynamically selects the best model for each test sample, enhancing generalization across subjects without target domain data.

Findings

Achieved state-of-the-art accuracy on SEED and Dreamer datasets.

Effectively mitigates inter-subject data drift in EEG emotion recognition.

Demonstrates robust online adaptation to unseen EEG data.

Abstract

Electroencephalography (EEG) emotion recognition plays a crucial role in human-computer interaction, particularly in healthcare and neuroscience. While supervised learning has been widely used, its reliance on manual annotations introduces high costs and potential bias. Self-supervised learning (SSL) offers a promising alternative by generating labels through pretext tasks. However, high inter-subject variability in EEG signals leads to significant data drift, limiting self-supervised models' generalization across unseen subjects. Traditional domain adaptation (DA) methods require access to target-domain data during training. Although domain generalization (DG) avoids this constraint, it often falls short in handling complex data drift due to limited coverage of possible target distributions. To tackle these challenges, we propose MMOC, a self-supervised framework with multi-model online collaboration (MMOC), to achieve online adaptation to unseen data. MMOC trains multiple base models using diverse strategies rooted in reconstruction and contrastive learning, enabling each model to develop distinct generalization capabilities. During inference, MMOC dynamically activates the most suitable model for each test sample via a loss-based routing mechanism that evaluates both contrastive and reconstruction losses. This dual consideration allows for a comprehensive measurement of data drift at both structural and semantic levels. Experimental results on the SEED and Dreamer datasets show that MMOC achieves state-of-the-art performance: 85.39% on SEED, and 68.77% and 69.37% on Dreamer arousal and valence dimensions, respectively. MMOC effectively mitigates inter-subject data drift, offering a practical solution for real-world EEG emotion recognition.