RepSPD: Enhancing SPD Manifold Representation in EEGs via Dynamic Graphs
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912928424263680 |
|---|---|
| author | Jia, Haohui Chen, Zheng Zhu, Lingwei Cao, Xu Matsubara, Yasuko Matsubara, Takashi Sakurai, Yasushi |
| author_facet | Jia, Haohui Chen, Zheng Zhu, Lingwei Cao, Xu Matsubara, Yasuko Matsubara, Takashi Sakurai, Yasushi |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_22981 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | RepSPD: Enhancing SPD Manifold Representation in EEGs via Dynamic Graphs Jia, Haohui Chen, Zheng Zhu, Lingwei Cao, Xu Matsubara, Yasuko Matsubara, Takashi Sakurai, Yasushi Artificial Intelligence 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. |
| title | RepSPD: Enhancing SPD Manifold Representation in EEGs via Dynamic Graphs |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2602.22981 |