We propose pairwise alignment of representations for semi-supervised Electroencephalogram (EEG) learning (PARSE), a novel semi-supervised architecture for learning reliable EEG representations for emotion recognition. To reduce the potential distribution mismatch between large amounts of unlabeled data and a limited number 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. The model is then followed by sharpening the guessed labels and convex combinations of the unlabeled and labeled data. Finally, it performs representation alignment and emotion classification. 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 performing the distribution alignment between unlabeled and labeled data, especially when only 1 sample per class is labeled. The source code of our article is publicly available at https://github.com/guangyizhangbci/PARSE.

中文翻译：

---

PARSE：用于情绪识别的半监督脑电图学习中表示的成对对齐


我们提出了半监督脑电图（EEG）学习（PARSE）的表示成对对齐，这是一种新颖的半监督架构，用于学习可靠的脑电图表示以进行情感识别。为了减少大量未标记数据和有限数量标记数据之间潜在的分布不匹配，PARSE 使用成对表示对齐。首先，我们的模型执行数据增强，然后对大量原始和增强的未标记数据进行标签猜测。然后，该模型会锐化猜测的标签以及未标记和标记数据的凸组合。最后，它执行表示对齐和情感分类。为了严格测试我们的模型，我们将 PARSE 与几种最先进的半监督方法进行比较，我们将其实施并适应脑电图学习。我们在四个基于脑电图的公共情绪识别数据集 SEED、SEED-IV、SEED-V 和 AMIGOS（价和唤醒）上进行这些实验。实验表明，我们提出的框架在 SEED、SEED-IV 和 AMIGOS（价）中使用不同数量的有限标记样本实现了总体最佳结果，同时在 SEED-V 和 AMIGOS 中接近总体最佳结果（达到第二好） （唤醒）。分析表明，我们的成对表示对齐通过在未标记和标记数据之间执行分布对齐，显着提高了性能，特别是当每个类仅标记 1 个样本时。我们文章的源代码可在 https://github.com/guangyizhangbci/PARSE 公开获取。