Separating personal from population gains when calibrating EEG foundation models for new users
Abstract
Every new user of a motor imagery brain-computer interface must be calibrated, and users typically return on different days. A common approach with electroencephalography (EEG) foundation models fits a small personal adapter on a frozen backbone, but evaluations are usually confined to one session and rarely separate the user's own contribution from that of the population model. We quantified personal adapters with two paired contrasts, the net gain of a user's own adapter over the population model and its advantage over adapters fitted to other users, for three frozen foundation models (CBraMod, REVE and LaBraM). In 235 held-out subjects from three datasets, same-session calibration produced a positive net gain in all nine model and dataset combinations (means of 1.5 to 5.4 percentage points), and the gain remained positive when population training was quadrupled. In 54 two-session subjects, adapters fitted on the first day still improved on the population model on the second day by 1.31 points for REVE and 1.64 points for LaBraM (Holm-adjusted p<0.01), retaining 61% and 83% of the gain from same-day recalibration, whereas the gain for CBraMod was 0.04 points and indistinguishable from zero. Same-day recalibration gave the highest mean accuracy for all three models, and adding 5 to 20 second-day labels to the first-day adapter mostly fell short of it. Whether personal adapters carry over across sessions therefore depends on the model and must be tested per model, and personalization should be reported against both a population reference and exchanged parameters, including across sessions.
Related
- Orientation detection for self-calibrating neuromorphic systems
- Representing Sex in Cardiovascular Models: Calibrating Reference Parameters from Healthy Cohorts
- Decoding antibody-antigen recognition: the BL8 language and its application in calibrating deep learning predictions
- Flourishing in university students: cross-sectional associations with personal and social FoMO, loneliness, and belonging
- Maintaining cognitive gains in type 2 diabetes: Barriers, supports, and patterns of strategy use
BibTeX
@misc{tao2026separating,
title = {{Separating personal from population gains when calibrating EEG foundation models for new users}},
author = {Xilin Tao and Kani Chen},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.34801},
eprint = {2609.34801},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.34801},
}
RIS
TY - UNPB
TI - Separating personal from population gains when calibrating EEG foundation models for new users
AU - Xilin Tao
AU - Kani Chen
PY - 2026
DA - 2026/09/28
PB - arXiv
DO - 10.48550/arxiv.2609.34801
UR - https://arxiv.org/abs/2609.34801
AB - Every new user of a motor imagery brain-computer interface must be calibrated, and users typically return on different days. A common approach with electroencephalography (EEG) foundation models fits a small personal adapter on a frozen backbone, but evaluations are usually confined to one session and rarely separate the user's own contribution from that of the population model. We quantified personal adapters with two paired contrasts, the net gain of a user's own adapter over the population model and its advantage over adapters fitted to other users, for three frozen foundation models (CBraMod, REVE and LaBraM). In 235 held-out subjects from three datasets, same-session calibration produced a positive net gain in all nine model and dataset combinations (means of 1.5 to 5.4 percentage points), and the gain remained positive when population training was quadrupled. In 54 two-session subjects, adapters fitted on the first day still improved on the population model on the second day by 1.31 points for REVE and 1.64 points for LaBraM (Holm-adjusted p<0.01), retaining 61% and 83% of the gain from same-day recalibration, whereas the gain for CBraMod was 0.04 points and indistinguishable from zero. Same-day recalibration gave the highest mean accuracy for all three models, and adding 5 to 20 second-day labels to the first-day adapter mostly fell short of it. Whether personal adapters carry over across sessions therefore depends on the model and must be tested per model, and personalization should be reported against both a population reference and exchanged parameters, including across sessions.
ER -