Self-supervised representation learning from electroencephalography signals

TL;DR

This paper introduces self-supervised learning methods for EEG signals, enabling effective feature extraction from unlabeled data, which improves performance in sleep scoring tasks especially with limited labeled data.

Contribution

The authors propose novel self-supervised strategies for EEG representation learning, demonstrating their effectiveness on sleep scoring with improved results over supervised methods.

Findings

Outperforms supervised learning in low data regimes

Captures important physiological information without labels

Effective on clinically relevant EEG datasets

Abstract

The supervised learning paradigm is limited by the cost - and sometimes the impracticality - of data collection and labeling in multiple domains. Self-supervised learning, a paradigm which exploits the structure of unlabeled data to create learning problems that can be solved with standard supervised approaches, has shown great promise as a pretraining or feature learning approach in fields like computer vision and time series processing. In this work, we present self-supervision strategies that can be used to learn informative representations from multivariate time series. One successful approach relies on predicting whether time windows are sampled from the same temporal context or not. As demonstrated on a clinically relevant task (sleep scoring) and with two electroencephalography datasets, our approach outperforms a purely supervised approach in low data regimes, while capturing important physiological information without any access to labels.