SCOPE: Structured Prototype-Guided Adaptation for EEG Foundation Models with Limited Labels

TL;DR

SCOPE is a novel framework that enhances EEG foundation model adaptation with limited labels by using structured supervision and confidence-aware pseudo-labels, improving performance and stability.

Contribution

It introduces a structured, confidence-aware adaptation method with external supervision and a prototype-conditioned adapter for EEG models with limited labels.

Findings

SCOPE outperforms existing methods across 50 adaptation settings.

It maintains high performance with as low as 5% labeled subjects.

SCOPE is efficient and versatile across multiple EEG tasks and models.

Abstract

Electroencephalography (EEG) foundation models (EFMs) have shown strong potential for transferable representation learning, yet their adaptation in realistic settings remains challenging when only a few labeled subjects are available. We show that this challenge stems from a structural mismatch between noisy, limited supervision and the highly plastic parameter space of EFMs, reflected in three key failure modes: overconfident miscalibration, prediction collapse, and representation drift caused by unconstrained parameter updates. To address these challenges, we propose SCOPE, a Structured COnfidence-aware Prototype-guided framework for label-limited EFM adaptation. SCOPE first constructs cohort-level external supervision to provide persistent guidance and further derives confidence-aware pseudo-labels to select reliable unlabeled samples for adaptation. Building on the constructed external supervision, SCOPE introduces ProAdapter, a lightweight prototype-conditioned adapter that modulates frozen EFMs to preserve pretrained representations. Experiments across 50 label-limited adaptation settings, covering 6 EEG tasks, 5 EFM backbones, and 5%-50% training labeled-subject ratios, show that SCOPE consistently achieves strong performance and efficiency.