MAtt: A Manifold Attention Network for EEG Decoding
This work addresses the problem of noisy EEG data decoding for non-invasive brain-computer interfaces, representing an incremental improvement by merging deep learning with geometric learning.
The authors tackled EEG signal decoding for brain-computer interfaces by proposing a manifold attention network (MAtt) that integrates deep neural networks with geometric learning on a Riemannian manifold, achieving superior performance over leading deep-learning methods on both time-synchronous and asynchronous EEG datasets.
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.