Siamese Sleep Transformer For Robust Sleep Stage Scoring With Self-knowledge Distillation and Selective Batch Sampling

TL;DR

This paper introduces a Siamese sleep transformer that enhances sleep stage scoring robustness by addressing dataset label bias and training instability through self-knowledge distillation and selective batch sampling.

Contribution

The study presents a novel Siamese sleep transformer with a selective batch sampling strategy and self-knowledge distillation to improve robustness and reduce performance variability.

Findings

SST achieved competitive sleep stage scoring performance across different datasets.

Selective batch sampling reduced performance variability during training.

The model effectively mitigated label bias effects in datasets.

Abstract

In this paper, we propose a Siamese sleep transformer (SST) that effectively extracts features from single-channel raw electroencephalogram signals for robust sleep stage scoring. Despite the significant advances in sleep stage scoring in the last few years, most of them mainly focused on the increment of model performance. However, other problems still exist: the bias of labels in datasets and the instability of model performance by repetitive training. To alleviate these problems, we propose the SST, a novel sleep stage scoring model with a selective batch sampling strategy and self-knowledge distillation. To evaluate how robust the model was to the bias of labels, we used different datasets for training and testing: the sleep heart health study and the Sleep-EDF datasets. In this condition, the SST showed competitive performance in sleep stage scoring. In addition, we demonstrated the effectiveness of the selective batch sampling strategy with a reduction of the standard deviation of performance by repetitive training. These results could show that SST extracted effective learning features against the bias of labels in datasets, and the selective batch sampling strategy worked for the model robustness in training.