English

Towards Sleep Scoring Generalization Through Self-Supervised Meta-Learning

Machine Learning 2022-07-29 v1

Abstract

In this work we introduce a novel meta-learning method for sleep scoring based on self-supervised learning. Our approach aims at building models for sleep scoring that can generalize across different patients and recording facilities, but do not require a further adaptation step to the target data. Towards this goal, we build our method on top of the Model Agnostic Meta-Learning (MAML) framework by incorporating a self-supervised learning (SSL) stage, and call it S2MAML. We show that S2MAML can significantly outperform MAML. The gain in performance comes from the SSL stage, which we base on a general purpose pseudo-task that limits the overfitting to the subject-specific patterns present in the training dataset. We show that S2MAML outperforms standard supervised learning and MAML on the SC, ST, ISRUC, UCD and CAP datasets.

Keywords

Cite

@article{arxiv.2207.13801,
  title  = {Towards Sleep Scoring Generalization Through Self-Supervised Meta-Learning},
  author = {Abdelhak Lemkhenter and Paolo Favaro},
  journal= {arXiv preprint arXiv:2207.13801},
  year   = {2022}
}

Comments

EMBC 2022

R2 v1 2026-06-25T01:17:24.228Z