RepSPD: Enhancing SPD Manifold Representation in EEGs via Dynamic Graphs

TL;DR

RepSPD is a geometric deep learning model that improves EEG analysis by integrating dynamic graph-based connectivity with SPD manifold representations, leading to better robustness and generalization.

Contribution

It introduces a novel cross-attention mechanism on the Riemannian manifold and a global alignment strategy to enhance SPD-based EEG representations.

Findings

Significantly outperforms existing EEG representation methods

Demonstrates superior robustness and generalization

Effectively captures frequency-specific synchronization and local topological structures

Abstract

Decoding brain activity from electroencephalography (EEG) is crucial for neuroscience and clinical applications. Among recent advances in deep learning for EEG, geometric learning stands out as its theoretical underpinnings on symmetric positive definite (SPD) allows revealing structural connectivity analysis in a physics-grounded manner. However, current SPD-based methods focus predominantly on statistical aggregation of EEGs, with frequency-specific synchronization and local topological structures of brain regions neglected. Given this, we propose RepSPD, a novel geometric deep learning (GDL)-based model. RepSPD implements a cross-attention mechanism on the Riemannian manifold to modulate the geometric attributes of SPD with graph-derived functional connectivity features. On top of this, we introduce a global bidirectional alignment strategy to reshape tangent-space embeddings, mitigating geometric distortions caused by curvature and thereby enhancing geometric consistency. Extensive experiments demonstrate that our proposed framework significantly outperforms existing EEG representation methods, exhibiting superior robustness and generalization capabilities.