# Label-Efficient Sleep Staging Using Transformers Pre-trained with Position Prediction

arXiv: https://arxiv.org/abs/2404.15308 · HTML: https://mlsanity.com/paper/2404.15308/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 14 references that are in the map.
- First posted on arXiv 29 Mar 2024.

## Builds on (most cited first, 8 of 8)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [SleepTransformer: Automatic Sleep Staging with Interpretability and Uncertainty Quantification](https://mlsanity.com/paper/2105.11043/) (2021)
- [MAEEG: Masked Auto-encoder for EEG Representation Learning](https://mlsanity.com/paper/2211.02625/) (2022)
- [Automatic Sleep Staging of EEG Signals: Recent Development, Challenges, and Future Directions](https://mlsanity.com/paper/2111.08446/) (2021)
- [Towards More Accurate Automatic Sleep Staging via Deep Transfer Learning](https://mlsanity.com/paper/1907.13177/) (2019)
- [Self-supervised representation learning from electroencephalography signals](https://mlsanity.com/paper/1911.05419/) (2019)
- [Position Prediction as an Effective Pretraining Strategy](https://mlsanity.com/paper/2207.07611/) (2022)

## Built on by (most cited first, 1 of 1)

- [Learning the relative composition of EEG signals using pairwise relative shift pretraining](https://mlsanity.com/paper/2511.11940/) (2025)

## Abstract (arXiv)

Sleep staging is a clinically important task for diagnosing various sleep disorders, but remains challenging to deploy at scale because it because it is both labor-intensive and time-consuming. Supervised deep learning-based approaches can automate sleep staging but at the expense of large labeled datasets, which can be unfeasible to procure for various settings, e.g., uncommon sleep disorders. While self-supervised learning (SSL) can mitigate this need, recent studies on SSL for sleep staging have shown performance gains saturate after training with labeled data from only tens of subjects, hence are unable to match peak performance attained with larger datasets. We hypothesize that the rapid saturation stems from applying a sub-optimal pretraining scheme that pretrains only a portion of the architecture, i.e., the feature encoder, but not the temporal encoder; therefore, we propose adopting an architecture that seamlessly couples the feature and temporal encoding and a suitable pretraining scheme that pretrains the entire model. On a sample sleep staging dataset, we find that the proposed scheme offers performance gains that do not saturate with amount of labeled training data (e.g., 3-5% improvement in balanced sleep staging accuracy across low- to high-labeled data settings), reducing the amount of labeled training data needed for high performance (e.g., by 800 subjects). Based on our findings, we recommend adopting this SSL paradigm for subsequent work on SSL for sleep staging.