MAEEG: Masked Auto-encoder for EEG Representation Learning

Hsiang-Yun Sherry Chien, Hanlin Goh, Christopher Michael Sandino, Joseph Yitan Cheng

Keywords: sleep stage classification, representation learning, EEG, bio-signal, self-supervised learning

TL;DR: We propose a self-supervised learning model, MAEEG, to learn EEG representations which improve sleep stage classification.

Abstract: 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.