Subject-Aware Contrastive Learning for Biosignals
This work addresses challenges in biosignal analysis for medical or research applications, but it is incremental as it builds on existing contrastive learning approaches with domain-specific adaptations.
The paper tackled the problem of noisy labels and limited subjects in biosignal datasets like EEG and ECG by proposing a self-supervised contrastive learning method with subject-aware techniques, resulting in competitive classification performance compared to fully supervised methods and improved representation quality through subject-invariance.
Datasets for biosignals, such as electroencephalogram (EEG) and electrocardiogram (ECG), often have noisy labels and have limited number of subjects (<100). To handle these challenges, we propose a self-supervised approach based on contrastive learning to model biosignals with a reduced reliance on labeled data and with fewer subjects. In this regime of limited labels and subjects, intersubject variability negatively impacts model performance. Thus, we introduce subject-aware learning through (1) a subject-specific contrastive loss, and (2) an adversarial training to promote subject-invariance during the self-supervised learning. We also develop a number of time-series data augmentation techniques to be used with the contrastive loss for biosignals. Our method is evaluated on publicly available datasets of two different biosignals with different tasks: EEG decoding and ECG anomaly detection. The embeddings learned using self-supervision yield competitive classification results compared to entirely supervised methods. We show that subject-invariance improves representation quality for these tasks, and observe that subject-specific loss increases performance when fine-tuning with supervised labels.