SPEED: Scalable Preprocessing of EEG Data for Self-Supervised Learning
This work addresses a domain-specific problem for EEG researchers by providing a scalable preprocessing method to enhance self-supervised learning applications.
The paper tackles the challenge of inefficient preprocessing for large-scale EEG data in self-supervised learning by proposing an optimized Python-based pipeline, which stabilizes training and improves downstream task performance compared to using raw data.
Electroencephalography (EEG) research typically focuses on tasks with narrowly defined objectives, but recent studies are expanding into the use of unlabeled data within larger models, aiming for a broader range of applications. This addresses a critical challenge in EEG research. For example, Kostas et al. (2021) show that self-supervised learning (SSL) outperforms traditional supervised methods. Given the high noise levels in EEG data, we argue that further improvements are possible with additional preprocessing. Current preprocessing methods often fail to efficiently manage the large data volumes required for SSL, due to their lack of optimization, reliance on subjective manual corrections, and validation processes or inflexible protocols that limit SSL. We propose a Python-based EEG preprocessing pipeline optimized for self-supervised learning, designed to efficiently process large-scale data. This optimization not only stabilizes self-supervised training but also enhances performance on downstream tasks compared to training with raw data.