Towards Sleep Scoring Generalization Through Self-Supervised Meta-Learning

TL;DR

This paper introduces S2MAML, a self-supervised meta-learning approach for sleep scoring that generalizes across patients and recording settings without needing adaptation, outperforming existing methods.

Contribution

The paper proposes S2MAML, combining self-supervised learning with meta-learning to improve sleep scoring generalization across diverse datasets.

Findings

S2MAML significantly outperforms MAML and supervised learning.

The SSL stage reduces overfitting to subject-specific patterns.

S2MAML achieves superior results on multiple sleep datasets.

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.