MAEEG: Masked Auto-encoder for EEG Representation Learning
This work addresses the problem of small datasets and labeling difficulties in EEG analysis for researchers and clinicians, though it is incremental as it adapts existing self-supervised methods to EEG.
The paper tackles the challenge of decoding EEG signals with limited labeled data by proposing MAEEG, a masked auto-encoder for self-supervised learning, which improves sleep stage classification accuracy by approximately 5% when few labels are available.
Decoding information from bio-signals such as EEG, using machine learning has been a challenge due to the small data-sets and difficulty to obtain labels. We propose a reconstruction-based self-supervised learning model, the masked auto-encoder for EEG (MAEEG), for learning EEG representations by learning to reconstruct the masked EEG features using a transformer architecture. We found that MAEEG can learn representations that significantly improve sleep stage classification (~5% accuracy increase) when only a small number of labels are given. We also found that input sample lengths and different ways of masking during reconstruction-based SSL pretraining have a huge effect on downstream model performance. Specifically, learning to reconstruct a larger proportion and more concentrated masked signal results in better performance on sleep classification. Our findings provide insight into how reconstruction-based SSL could help representation learning for EEG.