Metraipolis › archive › dc_8d456d8a716c
SPDAlign: Interpretable Riemannian Alignment for EEG Forward Modeling Shifts — arXiv:2610.06315
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.06315
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T05:31:35.667Z
- SHA-256 of the archived text
6f5fd881284433bfba1528e7d17da4702629281004bfbbb2203b8e327dfaa040- Stable URL of this page
https://metraipolis.com/documento/dc_8d456d8a716c
How to cite
SPDAlign: Interpretable Riemannian Alignment for EEG Forward Modeling Shifts — arXiv:2610.06315 — arXiv, https://arxiv.org/abs/2610.06315 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8d456d8a716c (Metraipolis archive dc_8d456d8a716c, sha256 6f5fd881284433bfba1528e7d17da4702629281004bfbbb2203b8e327dfaa040)
BibTeX
@misc{dc8d456d8a716c,
title = {SPDAlign: Interpretable Riemannian Alignment for EEG Forward Modeling Shifts — arXiv:2610.06315},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.06315},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8d456d8a716c; sha256 6f5fd881284433bfba1528e7d17da4702629281004bfbbb2203b8e327dfaa040},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.06315. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Electroencephalography (EEG) based brain-computer interfaces enable direct brain-to-device communication for applications such as rehabilitation and communication. However, their practical utility is often limited as the non-stationary nature of the EEG data introduces distribution shifts across domains (e.g., sessions and subjects). Adapting machine learning models to be invariant to these shifts in an unsupervised way, without using costly labeled calibration data, would drastically improve the utility of EEG data. In this work, we use a classic generative model of EEG to study distribution shifts introduced by the domain-specific forward process, which is associated with factors such as head geometry. We theoretically show that such distribution shifts can be recovered solely through linear transformations on the Symmetric Positive Definite manifold. Building on this insight, we propose SPDAlign, an interpretable framework for promoting domain-invariant EEG learning. SPDAlign first aligns the domain-specific means and corrects global rotations across domains using a recent optimal transport technique called Wasserstein Procrustes. We systematically study the proposed approach through simulations and demonstrate its competitive performance on extensive public EEG datasets. Additionally, SPDAlign is a globally linear framework and is intrinsically interpretable, so that the framework can identify frequency ranges of interest, determine the spatial patterns reflecting source-sensor relationships, and address cross-subject variability. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.06315 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-06T05:27:05.878Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).