Test-Time Adaptation for EEG Foundation Models: A Systematic Study under Real-World Distribution Shifts

Gabriel Jason Lee, Jathurshan Pradeepkumar, Jimeng Sun
Proceedings of the 11th Machine Learning for Healthcare Conference, PMLR 340:948-984, 2026.

Abstract

Electroencephalography (EEG) foundation models have shown strong potential for learning generalizable representations from large-scale neural data, yet their clinical deployment is hindered by distribution shifts across clinical settings, devices, and populations. Test-time adaptation (TTA) offers a promising solution by enabling models to adapt to unlabeled target data during inference without access to source data, a valuable property in healthcare settings constrained by privacy regulations and limited labeled data. However, its effectiveness for EEG remains largely underexplored. In this work, we introduce NeuroAdapt-Bench, a systematic benchmark for evaluating test-time adaptation methods on EEG foundation models under realistic distribution shifts. We evaluate representative TTA approaches from other domains across multiple pretrained foundation models, diverse downstream tasks, and heterogeneous datasets spanning in-distribution, out-of-distribution, and extreme modality shifts (e.g., Ear-EEG). Our results show that the evaluated TTA methods yield inconsistent gains and often degrade performance, with gradient-based approaches particularly prone to heavy degradation and optimization-free methods showing greater stability. For the evaluated EEG foundation models and representative TTA methods, these findings highlight the limitations of directly applying existing TTA techniques to EEG and underscore the need for domain-specific adaptation strategies. Code is available at https://github.com/leegabriel/NeuroAdapt-Bench.

Cite this Paper

BibTeX
@InProceedings{pmlr-v340-lee26a, title = {Test-Time Adaptation for EEG Foundation Models: A Systematic Study under Real-World Distribution Shifts}, author = {Lee, Gabriel Jason and Pradeepkumar, Jathurshan and Sun, Jimeng}, booktitle = {Proceedings of the 11th Machine Learning for Healthcare Conference}, pages = {948--984}, year = {2026}, editor = {Krishnan, Rahul G. and van Amsterdam, Wouter A. C. and Chopra, Sumit and Overgaard, Shauna and Hughes, Michael and Ötleş, Erkin and Shen, Yiqiu and Shanmugam, Divya and Nayan, Madhur and Engelhard, Matthew and Fackler, Jim and Oberst, Michael}, volume = {340}, series = {Proceedings of Machine Learning Research}, month = {12--14 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v340/main/assets/lee26a/lee26a.pdf}, url = {https://proceedings.mlr.press/v340/lee26a.html}, abstract = {Electroencephalography (EEG) foundation models have shown strong potential for learning generalizable representations from large-scale neural data, yet their clinical deployment is hindered by distribution shifts across clinical settings, devices, and populations. Test-time adaptation (TTA) offers a promising solution by enabling models to adapt to unlabeled target data during inference without access to source data, a valuable property in healthcare settings constrained by privacy regulations and limited labeled data. However, its effectiveness for EEG remains largely underexplored. In this work, we introduce NeuroAdapt-Bench, a systematic benchmark for evaluating test-time adaptation methods on EEG foundation models under realistic distribution shifts. We evaluate representative TTA approaches from other domains across multiple pretrained foundation models, diverse downstream tasks, and heterogeneous datasets spanning in-distribution, out-of-distribution, and extreme modality shifts (e.g., Ear-EEG). Our results show that the evaluated TTA methods yield inconsistent gains and often degrade performance, with gradient-based approaches particularly prone to heavy degradation and optimization-free methods showing greater stability. For the evaluated EEG foundation models and representative TTA methods, these findings highlight the limitations of directly applying existing TTA techniques to EEG and underscore the need for domain-specific adaptation strategies. Code is available at https://github.com/leegabriel/NeuroAdapt-Bench.} }
Endnote
%0 Conference Paper %T Test-Time Adaptation for EEG Foundation Models: A Systematic Study under Real-World Distribution Shifts %A Gabriel Jason Lee %A Jathurshan Pradeepkumar %A Jimeng Sun %B Proceedings of the 11th Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2026 %E Rahul G. Krishnan %E Wouter A. C. van Amsterdam %E Sumit Chopra %E Shauna Overgaard %E Michael Hughes %E Erkin Ötleş %E Yiqiu Shen %E Divya Shanmugam %E Madhur Nayan %E Matthew Engelhard %E Jim Fackler %E Michael Oberst %F pmlr-v340-lee26a %I PMLR %P 948--984 %U https://proceedings.mlr.press/v340/lee26a.html %V 340 %X Electroencephalography (EEG) foundation models have shown strong potential for learning generalizable representations from large-scale neural data, yet their clinical deployment is hindered by distribution shifts across clinical settings, devices, and populations. Test-time adaptation (TTA) offers a promising solution by enabling models to adapt to unlabeled target data during inference without access to source data, a valuable property in healthcare settings constrained by privacy regulations and limited labeled data. However, its effectiveness for EEG remains largely underexplored. In this work, we introduce NeuroAdapt-Bench, a systematic benchmark for evaluating test-time adaptation methods on EEG foundation models under realistic distribution shifts. We evaluate representative TTA approaches from other domains across multiple pretrained foundation models, diverse downstream tasks, and heterogeneous datasets spanning in-distribution, out-of-distribution, and extreme modality shifts (e.g., Ear-EEG). Our results show that the evaluated TTA methods yield inconsistent gains and often degrade performance, with gradient-based approaches particularly prone to heavy degradation and optimization-free methods showing greater stability. For the evaluated EEG foundation models and representative TTA methods, these findings highlight the limitations of directly applying existing TTA techniques to EEG and underscore the need for domain-specific adaptation strategies. Code is available at https://github.com/leegabriel/NeuroAdapt-Bench.
APA
Lee, G.J., Pradeepkumar, J. & Sun, J.. (2026). Test-Time Adaptation for EEG Foundation Models: A Systematic Study under Real-World Distribution Shifts. Proceedings of the 11th Machine Learning for Healthcare Conference, in Proceedings of Machine Learning Research 340:948-984 Available from https://proceedings.mlr.press/v340/lee26a.html.

Related Material