Metraipolis › archive › dc_7dc226fa8d66

Neural State Prediction: Obstructing Shortcut Learning in EEG Foundation Models — arXiv:2609.31167

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.31167
License (as archived)
CC0-1.0
Archived
2026-10-08T01:38:35.756Z
SHA-256 of the archived text
20a599f612dc32012dc3f03dafdc4cc581040f6fb7f2d9a56ce41ded53c4b2d3
Stable URL of this page
https://metraipolis.com/documento/dc_7dc226fa8d66

How to cite

Neural State Prediction: Obstructing Shortcut Learning in EEG Foundation Models — arXiv:2609.31167 — arXiv (en), https://arxiv.org/abs/2609.31167 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7dc226fa8d66 (Metraipolis archive dc_7dc226fa8d66, sha256 20a599f612dc32012dc3f03dafdc4cc581040f6fb7f2d9a56ce41ded53c4b2d3)
BibTeX
@misc{dc7dc226fa8d66,
  title = {Neural State Prediction: Obstructing Shortcut Learning in EEG Foundation Models — arXiv:2609.31167},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.31167},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7dc226fa8d66; sha256 20a599f612dc32012dc3f03dafdc4cc581040f6fb7f2d9a56ce41ded53c4b2d3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.31167. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

EEG foundation models increasingly use masked prediction to learn from unlabeled recordings, but optimizing this objective does not ensure transferable neural representations. A central challenge is that stable positional cues and local correlations can make masked regions predictable without integrating distributed neural context. To reduce this reliance on low-information prediction paths, we introduce Neural State Prediction (NSP), a latent-predictive framework that constrains both the prediction target and the available context. NSP uses a Target Encoder updated by an exponential moving average (EMA) to define latent supervision. Identity residualization removes additive effects associated with channel identity and relative time from the targets, while topology-separated context excludes their immediate spatial and temporal neighborhood from the visible input. We pretrain NSP on 2.2 million EEG segments from TUEG and evaluate it across 30 downstream datasets spanning clinical diagnosis, sleep staging, emotion recognition, motor imagery, event-related potentials, cognitive-state decoding, and language retrieval. Under full-parameter multi-task fine-tuning on EEG-FM-Bench, NSP achieves 63.94 macro balanced accuracy across 14 datasets, exceeding the strongest evaluated baseline by 2.35 percentage points. Controlled component ablations assess the contribution of each mechanism, while matched context controls and held-out interventions characterize the role of context geometry, signal content, and positional information. Jointly designing latent targets and their context offers a promising direction for EEG foundation models that learn from distributed signal structure.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-28 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.31167 — 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 2026-10-08T01:12:14.349Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).