SS-EMERGE - self-supervised enhancement for multidimension emotion recognition using GNNs for EEG

Abstract

Abstract Self-supervised learning (SSL) is a potent method for leveraging unlabelled data. Nonetheless, EEG signals, characterised by their low signal-to-noise ratio and high-frequency attributes, often do not surpass fully-supervised techniques in cross-subject tasks such as Emotion Recognition. Therefore, this study introduces a hybrid SSL framework: Self-Supervised Enhancement for Multidimension Emotion Recognition using Graph Neural Networks (SS-EMERGE). This model enhances cross-subject EEG-based emotion recognition by incorporating Causal Convolutions for temporal feature extraction, Graph Attention Transformers (GAT) for spatial modelling, and Spectral Embedding for spectral domain analysis. The approach utilises meiosis-based contrastive learning for pretraining, followed by fine-tuning with minimal labelled data, thereby enriching dataset diversity and specificity. Evaluations on the widely-used Emotion recognition datasets, SEED and SEED-IV, reveal that SS-EMERGE achieves impressive Leave-One-Subject-Out (LOSO) accuracies of 92.35% and 81.51%, respectively. It also proposes a foundation model pre-trained on combined SEED and SEED-IV datasets, demonstrating performance comparable to individual models. These results emphasise the potential of SS-EMERGE in advancing EEG-based emotion recognition with high accuracy and minimal labelled data.

Keywords

• EEG
• Self-Supervised Learning
• GNN
• Constrastive Learning
• Cross-Subject Emotion Recognition