EEGFormer: Towards Transferable and Interpretable Large-Scale EEG Foundation Model

TL;DR

EEGFormer is a large-scale EEG foundation model trained with self-supervised learning, offering transferable, interpretable representations that improve performance across diverse EEG tasks and enhance understanding of brain signal patterns.

Contribution

The paper introduces EEGFormer, a novel large-scale EEG foundation model trained with self-supervised learning, enabling transferability and interpretability across multiple EEG applications.

Findings

Effective transfer to various downstream EEG tasks

Provides interpretable insights into EEG signal patterns

Demonstrates strong anomaly detection capabilities

Abstract

Self-supervised learning has emerged as a highly effective approach in the fields of natural language processing and computer vision. It is also applicable to brain signals such as electroencephalography (EEG) data, given the abundance of available unlabeled data that exist in a wide spectrum of real-world medical applications ranging from seizure detection to wave analysis. The existing works leveraging self-supervised learning on EEG modeling mainly focus on pretraining upon each individual dataset corresponding to a single downstream task, which cannot leverage the power of abundant data, and they may derive sub-optimal solutions with a lack of generalization. Moreover, these methods rely on end-to-end model learning which is not easy for humans to understand. In this paper, we present a novel EEG foundation model, namely EEGFormer, pretrained on large-scale compound EEG data. The pretrained model cannot only learn universal representations on EEG signals with adaptable performance on various downstream tasks but also provide interpretable outcomes of the useful patterns within the data. To validate the effectiveness of our model, we extensively evaluate it on various downstream tasks and assess the performance under different transfer settings. Furthermore, we demonstrate how the learned model exhibits transferable anomaly detection performance and provides valuable interpretability of the acquired patterns via self-supervised learning.