对比四种脑电通道适配方法，发现小模型也能超大模型。
Channel Adaptation for EEG Foundation Models: A Systematic Benchmark Across Architectures, Tasks, and Training Regimes
- 系统测试四类通道适配方法在五种模型上的表现
- 500万参数小模型在4/5任务上超越31倍大的模型
- 适配方法效果依赖模型架构，需谨慎选择
构建大规模脑电基础模型需融合不同电极布局的数据，这既是扩大预训练数据集的必要条件，也是下游部署的前提。本文首次系统比较了四种通道适配方法（卷积1D投影、球面样条插值SSI、源空间分解、黎曼重新中心化）在五种预训练脑电基础模型（500万至1.57亿参数）上的表现，涵盖五项下游任务及两种训练范式，每组实验重复10–15次。研究发现，固定布局模型（BENDR、Neuro-GPT）需外部适配，而灵活模型（EEGPT、CBraMod）在微调时可原生匹配或超越适配效果，但在冻结编码器部署下仍受益于外部方法。存在探针与微调（probe-SFT）不对称性：外部适配可能在灵活模型微调中引发严重负迁移。最优适配方法具有架构依赖性（BENDR用Conv1d，Neuro-GPT用SSI或黎曼方法，抑郁检测用源空间分解）。500万参数的CBraMod在4/5数据集上优于最大达31倍大的模型，与独立研究一致——紧凑的脑电专用架构可媲美更大模型。
原文摘要 · Abstract (English)
Scaling EEG foundation models requires pooling data across heterogeneous electrode montages, a prerequisite both for larger pretraining corpora and for downstream deployment. We present the first systematic comparison of four channel adaptation methods (Conv1d projection, spherical spline interpolation (SSI), source-space decomposition, and Riemannian re-centering) across five pretrained EEG foundation models (5M--157M parameters), five downstream tasks, and two training regimes with 10--15 random seeds each. We find that rigid-montage models (BENDR, Neuro-GPT) require external adaptation, while flexible models (EEGPT, CBraMod) match or exceed it natively when fine-tuned but benefit from external methods under frozen-encoder deployment. A probe-SFT asymmetry exists: external adaptation can cause severe negative transfer during fine-tuning of flexible models. The optimal method is architecture-dependent (Conv1d for BENDR, SSI/Riemannian for Neuro-GPT, source-space decomposition for depression detection), and 5M-parameter CBraMod outperforms models up to 31$\times$ larger on 4/5 datasets, consistent with independent findings that compact EEG-specific architectures can match larger models.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。