Pre-Training Graph Contrastive Masked Autoencoders are Strong Distillers for EEG
This work addresses the problem of data scarcity in EEG analysis for clinical applications, offering a novel distillation method that is incremental in combining existing self-supervised techniques.
The paper tackles the challenge of leveraging unlabeled high-density EEG data to enhance performance with limited labeled low-density EEG data by proposing EEG-DisGCMAE, a unified pre-trained graph contrastive masked autoencoder distiller, which achieves improved classification results across four tasks on two clinical EEG datasets.
Effectively utilizing extensive unlabeled high-density EEG data to improve performance in scenarios with limited labeled low-density EEG data presents a significant challenge. In this paper, we address this challenge by formulating it as a graph transfer learning and knowledge distillation problem. We propose a Unified Pre-trained Graph Contrastive Masked Autoencoder Distiller, named EEG-DisGCMAE, to bridge the gap between unlabeled and labeled as well as high- and low-density EEG data. Our approach introduces a novel unified graph self-supervised pre-training paradigm, which seamlessly integrates the graph contrastive pre-training with the graph masked autoencoder pre-training. Furthermore, we propose a graph topology distillation loss function, allowing a lightweight student model trained on low-density data to learn from a teacher model trained on high-density data during pre-training and fine-tuning. This method effectively handles missing electrodes through contrastive distillation. We validate the effectiveness of EEG-DisGCMAE across four classification tasks using two clinical EEG datasets with abundant data. The source code is available at https://github.com/weixinxu666/EEG_DisGCMAE.