Metraipolis › archive › dc_0e9daa482ec7

Parameter-Efficient Self-Supervised Adaptation for EEG-FM under Fixed Computational Budgets — arXiv:2608.24727

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.24727
License (as archived)
CC0-1.0
Archived
2026-10-18T06:36:23.820Z
SHA-256 of the archived text
cac9588525522ea1042e982347709aa4c7938b1c5e0b060981c30dc0ed5c3910
Stable URL of this page
https://metraipolis.com/documento/dc_0e9daa482ec7

How to cite

Parameter-Efficient Self-Supervised Adaptation for EEG-FM under Fixed Computational Budgets — arXiv:2608.24727 — arXiv (en), https://arxiv.org/abs/2608.24727 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0e9daa482ec7 (Metraipolis archive dc_0e9daa482ec7, sha256 cac9588525522ea1042e982347709aa4c7938b1c5e0b060981c30dc0ed5c3910)
BibTeX
@misc{dc0e9daa482ec7,
  title = {Parameter-Efficient Self-Supervised Adaptation for EEG-FM under Fixed Computational Budgets — arXiv:2608.24727},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.24727},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0e9daa482ec7; sha256 cac9588525522ea1042e982347709aa4c7938b1c5e0b060981c30dc0ed5c3910},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.24727. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

EEG foundation models pretrained via self-supervised learning promise transferable representations, but their generalization remains limited, especially across diverse clinical datasets. Full fine-tuning is impractical for resource-constrained clinical settings due to high computational requirements. In this work, we investigate whether parameter-efficient self-supervised adaptation, updating only 9% of parameters suffices to align representations to target tasks. We evaluate our method on two state-of-the-art models with different pretraining objectives: BIOT (contrastive) and CBraMod (masked reconstruction), and evaluate on three clinical EEG datasets for abnormality detection (TUAB), event classification (TUEV), and seizure detection (CHB-MIT) under both in-distribution and out-of-distribution conditions. SSL adaptation yields consistent gains over linear probing, up to 20x AUCPR. Under a fixed compute budget, peak performance requires only 20--50% of available unlabeled data. Critically, when total window count is fixed, performance remains invariant to patient count, suggesting that performance is dependent on overall temporal window diversity only. Our findings demonstrate that parameter-efficient adaptation enables effective deployment of EEG Foundation models (EEG-FM) with minimal computational overhead and data collection burden. Code available at: this https URL

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-26 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.24727 — 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 2026-10-18T06:28:52.276Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-26?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).