MAtt: A Manifold Attention Network for EEG Decoding

TL;DR

This paper introduces MAtt, a novel geometric deep learning model utilizing manifold attention on Riemannian manifolds, significantly improving EEG decoding performance and robustness over existing deep learning methods.

Contribution

The paper presents a new manifold attention network (MAtt) that combines deep neural networks with geometric learning on Riemannian manifolds for enhanced EEG decoding.

Findings

MAtt outperforms existing DL methods on EEG datasets.

The model effectively captures informative EEG features.

MAtt handles non-stationarity in brain dynamics.

Abstract

Recognition of electroencephalographic (EEG) signals highly affect the efficiency of non-invasive brain-computer interfaces (BCIs). While recent advances of deep-learning (DL)-based EEG decoders offer improved performances, the development of geometric learning (GL) has attracted much attention for offering exceptional robustness in decoding noisy EEG data. However, there is a lack of studies on the merged use of deep neural networks (DNNs) and geometric learning for EEG decoding. We herein propose a manifold attention network (mAtt), a novel geometric deep learning (GDL)-based model, featuring a manifold attention mechanism that characterizes spatiotemporal representations of EEG data fully on a Riemannian symmetric positive definite (SPD) manifold. The evaluation of the proposed MAtt on both time-synchronous and -asyncronous EEG datasets suggests its superiority over other leading DL methods for general EEG decoding. Furthermore, analysis of model interpretation reveals the capability of MAtt in capturing informative EEG features and handling the non-stationarity of brain dynamics.