PARSE: Pairwise Alignment of Representations in Semi-Supervised EEG Learning for Emotion Recognition
This work addresses the challenge of limited labeled data for EEG-based emotion recognition, which is important for applications in healthcare and human-computer interaction, but it is incremental as it builds on existing semi-supervised methods.
The authors tackled the problem of emotion recognition from EEG data with limited labeled samples by proposing PARSE, a semi-supervised architecture using pairwise representation alignment, which achieved the best results on three datasets and second-best on two others, with notable improvements when only 1 sample per class was labeled.
We propose PARSE, a novel semi-supervised architecture for learning strong EEG representations for emotion recognition. To reduce the potential distribution mismatch between the large amounts of unlabeled data and the limited amount of labeled data, PARSE uses pairwise representation alignment. First, our model performs data augmentation followed by label guessing for large amounts of original and augmented unlabeled data. This is then followed by sharpening of the guessed labels and convex combinations of the unlabeled and labeled data. Finally, representation alignment and emotion classification are performed. To rigorously test our model, we compare PARSE to several state-of-the-art semi-supervised approaches which we implement and adapt for EEG learning. We perform these experiments on four public EEG-based emotion recognition datasets, SEED, SEED-IV, SEED-V and AMIGOS (valence and arousal). The experiments show that our proposed framework achieves the overall best results with varying amounts of limited labeled samples in SEED, SEED-IV and AMIGOS (valence), while approaching the overall best result (reaching the second-best) in SEED-V and AMIGOS (arousal). The analysis shows that our pairwise representation alignment considerably improves the performance by reducing the distribution alignment between unlabeled and labeled data, especially when only 1 sample per class is labeled.