Learning the relative composition of EEG signals using pairwise relative shift pretraining

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sandino, Christopher, Lala, Sayeri, Chau, Geeling, Ayoughi, Melika, Mahasseni, Behrooz, Zippi, Ellen, Moin, Ali, Azemi, Erdrin, Goh, Hanlin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908654725234688
author Sandino, Christopher
Lala, Sayeri
Chau, Geeling
Ayoughi, Melika
Mahasseni, Behrooz
Zippi, Ellen
Moin, Ali
Azemi, Erdrin
Goh, Hanlin
author_facet Sandino, Christopher
Lala, Sayeri
Chau, Geeling
Ayoughi, Melika
Mahasseni, Behrooz
Zippi, Ellen
Moin, Ali
Azemi, Erdrin
Goh, Hanlin
contents Self-supervised learning (SSL) offers a promising approach for learning electroencephalography (EEG) representations from unlabeled data, reducing the need for expensive annotations for clinical applications like sleep staging and seizure detection. While current EEG SSL methods predominantly use masked reconstruction strategies like masked autoencoders (MAE) that capture local temporal patterns, position prediction pretraining remains underexplored despite its potential to learn long-range dependencies in neural signals. We introduce PAirwise Relative Shift or PARS pretraining, a novel pretext task that predicts relative temporal shifts between randomly sampled EEG window pairs. Unlike reconstruction-based methods that focus on local pattern recovery, PARS encourages encoders to capture relative temporal composition and long-range dependencies inherent in neural signals. Through comprehensive evaluation on various EEG decoding tasks, we demonstrate that PARS-pretrained transformers consistently outperform existing pretraining strategies in label-efficient and transfer learning settings, establishing a new paradigm for self-supervised EEG representation learning.
format Preprint
id arxiv_https___arxiv_org_abs_2511_11940
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning the relative composition of EEG signals using pairwise relative shift pretraining
Sandino, Christopher
Lala, Sayeri
Chau, Geeling
Ayoughi, Melika
Mahasseni, Behrooz
Zippi, Ellen
Moin, Ali
Azemi, Erdrin
Goh, Hanlin
Machine Learning
Signal Processing
Self-supervised learning (SSL) offers a promising approach for learning electroencephalography (EEG) representations from unlabeled data, reducing the need for expensive annotations for clinical applications like sleep staging and seizure detection. While current EEG SSL methods predominantly use masked reconstruction strategies like masked autoencoders (MAE) that capture local temporal patterns, position prediction pretraining remains underexplored despite its potential to learn long-range dependencies in neural signals. We introduce PAirwise Relative Shift or PARS pretraining, a novel pretext task that predicts relative temporal shifts between randomly sampled EEG window pairs. Unlike reconstruction-based methods that focus on local pattern recovery, PARS encourages encoders to capture relative temporal composition and long-range dependencies inherent in neural signals. Through comprehensive evaluation on various EEG decoding tasks, we demonstrate that PARS-pretrained transformers consistently outperform existing pretraining strategies in label-efficient and transfer learning settings, establishing a new paradigm for self-supervised EEG representation learning.
title Learning the relative composition of EEG signals using pairwise relative shift pretraining
topic Machine Learning
Signal Processing
url https://arxiv.org/abs/2511.11940