脑电基础模型的测试时适应：现实世界分布偏移下的系统性研究

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

April 18, 2026

作者: Gabriel Jason Lee, Jathurshan Pradeepkumar, Jimeng Sun

cs.AI

摘要

脑电图（EEG）基础模型在从大规模神经数据中学习可泛化表征方面展现出巨大潜力，但其临床应用仍受限于临床场景、采集设备和人群差异带来的分布偏移。测试时适应（TTA）通过使模型在推理过程中无需源数据即可适应无标注目标数据，为这一难题提供了可行解决方案——这一特性在受隐私法规和标注数据稀缺制约的医疗场景中尤为重要。然而，该方法在EEG领域的有效性仍亟待探索。本研究提出NeuroAdapt-Bench，一个用于评估EEG基础模型在现实分布偏移下测试时适应方法的系统性基准框架。我们在多种预训练基础模型、多样化下游任务以及涵盖域内分布、域外分布乃至极端模态偏移（如耳际EEG）的异构数据集上，评估了来自其他领域的代表性TTA方法。实验结果表明：标准TTA方法带来的性能提升不稳定，甚至常导致性能退化，其中基于梯度的方法尤其容易出现严重衰退；相比之下，无优化方法展现出更强的稳定性和更可靠的改进效果。这些发现既揭示了现有TTA技术在EEG领域的局限性，为未来发展提供了指引，也凸显了开发领域特异性适应策略的必要性。

English

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 standard TTA methods yield inconsistent gains and often degrade performance, with gradient-based approaches particularly prone to heavy degradation. In contrast, optimization-free methods demonstrate greater stability and more reliable improvements. These findings highlight the limitations of existing TTA techniques in EEG, provide guidance for future development, and underscore the need for domain-specific adaptation strategies.