A Unified SPD Token Transformer Framework for EEG Classification: Systematic Comparison of Geometric Embeddings
Authors:
Preprint
Abstract
Spatial covariance matrices of EEG signals are Symmetric Positive Definite (SPD) and lie on a Riemannian manifold, yet the theoretical connection between embedding geometry and optimization dynamics remains unexplored. We provide a formal analysis linking embedding choice to gradient conditioning and numerical stability for SPD manifolds, establishing three theoretical results: (1) BWSPD's $\sqrtκ$ gradient conditioning (vs $κ$ for Log-Euclidean) via Daleckii-Kreĭn matrices provides better gradient conditioning on high-dimensional inputs ($d \geq 22$), with this advantage reducing on low-dimensional inputs ($d \leq 8$) where eigendecomposition overhead dominates; (2) Embedding-Space Batch Normalization (BN-Embed) approximates Riemannian normalization up to $O(\varepsilon^2)$ error, yielding $+26\%$ accuracy on 56-channel ERP data but negligible effect on 8-channel SSVEP data, matching the channel-count-dependent prediction; (3) bi-Lipschitz bounds prove BWSPD tokens preserve manifold distances with distortion governed solely by the condition ratio $κ$. We validate these predictions via a unified Transformer framework comparing BWSPD, Log-Euclidean, and Euclidean embeddings within identical architecture across 1,500+ runs on three EEG paradigms (motor imagery, ERP, SSVEP; 36 subjects). Our Log-Euclidean Transformer achieves state-of-the-art performance on all datasets, substantially outperforming classical Riemannian classifiers and recent SPD baselines, while BWSPD offers competitive accuracy with similar training time.
Keywords
All Related Versions
This publication has 13 references indexed in Scilit:
- Physics-Informed Attention Temporal Convolutional Network for EEG-Based Motor Imagery ClassificationIEEE Transactions on Industrial Informatics, 2022
- EEGNet: a compact convolutional neural network for EEG-based brain–computer interfacesJournal of Neural Engineering, 2018
- A multimodal dataset for authoring and editing multimedia content: The MAMEM projectData in Brief, 2017
- Deep learning with convolutional neural networks for EEG decoding and visualizationHuman Brain Mapping, 2017
- Classification of covariance matrices using a Riemannian-based kernel for BCI applicationsNeurocomputing, 2013
- Multiclass Brain–Computer Interface Classification by Riemannian GeometryIEEE Transactions on Biomedical Engineering, 2012
- Optimizing Spatial filters for Robust EEG Single-Trial AnalysisIEEE Signal Processing Magazine, 2007
- Log‐Euclidean metrics for fast and simple calculus on diffusion tensorsMagnetic Resonance in Medicine, 2006
- A Riemannian Framework for Tensor ComputingInternational Journal of Computer Vision, 2006
- Free states of the canonical anticommutation relationsCommunications in Mathematical Physics, 1970