Metraipolis › archive › dc_0c6fa3855ea2
Dataset-Dependent Effects of Cross-Depth Aggregation and Soft-Routed Experts in EEG Foundation Model Fine-Tuning — arXiv:2609.17886
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.17886
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T15:04:28.932Z
- SHA-256 of the archived text
3fdc09f7bf32138aef72349d8f687b7bf0efb76973b3922e044b7701d80afa37- Stable URL of this page
https://metraipolis.com/documento/dc_0c6fa3855ea2
How to cite
Dataset-Dependent Effects of Cross-Depth Aggregation and Soft-Routed Experts in EEG Foundation Model Fine-Tuning — arXiv:2609.17886 — arXiv (en), https://arxiv.org/abs/2609.17886 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0c6fa3855ea2 (Metraipolis archive dc_0c6fa3855ea2, sha256 3fdc09f7bf32138aef72349d8f687b7bf0efb76973b3922e044b7701d80afa37)
BibTeX
@misc{dc0c6fa3855ea2,
title = {Dataset-Dependent Effects of Cross-Depth Aggregation and Soft-Routed Experts in EEG Foundation Model Fine-Tuning — arXiv:2609.17886},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.17886},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0c6fa3855ea2; sha256 3fdc09f7bf32138aef72349d8f687b7bf0efb76973b3922e044b7701d80afa37},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.17886. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
EEG decoding tasks can rely on different temporal dynamics and cross-channel relationships. We test whether specialized modules improve a fully fine-tuned EEG foundation model by augmenting CBraMod with cross-depth Attention Residuals (AttnRes) and two soft-routed expert banks. Across matched three-seed experiments on FACED, ISRUC, SEED-V, and PhysioNet-MI, the complete model changes mean balanced accuracy relative to full fine-tuning by -0.12, +1.27, +0.77, and -1.27 points, respectively. AttnRes alone improves mean balanced accuracy on three datasets, whereas adding experts on top of AttnRes helps only FACED and SEED-V. These gains come with substantial overhead: AttnRes requires 2.11 to 2.88x runtime and 1.78 to 2.67x memory, while the complete model requires 2.41 to 3.04x runtime and 1.86 to 2.85x memory. Overall, the added modules produce dataset-dependent, sometimes opposing effects rather than consistent gains over full fine-tuning. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-17 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.17886 — 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 2026-10-15T14:08:19.079Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).