arXiv：cs.LG· Jinzhou Wu, Baoping Tang, Qikang Li, Yi Wang, Cheng Li, Shujian Yu·· 3 小时前
脑基础模型引导的源选择域适应框架 BFM-MSDA，用于跨被试 EEG 解码
Brain foundation model-guided source-selective domain adaptation for cross-subject EEG decoding
AI 导读
研究提出脑基础模型引导的多源域适应框架 BFM-MSDA，用于跨被试运动想象 EEG 解码。该方法利用预训练脑基础模型表征估计源-目标兼容性并检索目标相关源，再以相关性加权双重对齐策略，用 Cauchy-Schwarz 散度和条件 Cauchy-Schwarz 散度分别对齐边际特征分布与类条件决策分布。
正文
Abstract:Cross-subject motor-imagery electroencephalography (MI-EEG) decoding remains challenging because substantial inter-subject variability can cause both negative transfer from poorly matched source subjects and persistent distribution discrepancies between source and target domains. Existing multi-source domain adaptation methods often incorporate all available source domains or estimate source relevance using signal-level or task-specific representations, while distribution alignment is frequently performed only at the feature level. These limitations may introduce irrelevant source knowledge and fail to preserve class-discriminative structures across subjects. In this study, we propose a brain foundation model-guided multi-source domain adaptation framework (BFM-MSDA) for cross-subject MI-EEG decoding. The method first utilizes representations learned by a pretrained brain foundation model to estimate source--target compatibility and retrieve target-relevant sources. Subsequently, a relevance-weighted dual alignment strategy is applied to the selected sources and the unlabeled target domain. Specifically, Cauchy--Schwarz (CS) divergence is used to reduce discrepancies in marginal feature distributions, while conditional Cauchy--Schwarz (CCS) divergence further aligns class-dependent decision distributions. Source relevance is incorporated into both alignment terms so that more transferable source subjects contribute more strongly to adaptation. Experiments on two public MI-EEG benchmarks achieve average accuracies of 86.16% and 78.41%, outperforming representative cross-subject decoding and domain adaptation methods. Additional experiments with a large source pool further demonstrate that target-aware source retrieval improves scalability while mitigating negative transfer. These results highlight the importance of informed source selection under cross-subject distribution shift.
| Comments: | 22 pages, 11 figures |
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2507.21037 [cs.LG] |
| (or arXiv:2507.21037v3 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2507.21037 arXiv-issued DOI via DataCite |
Submission history
From: Jinzhou Wu Mr [view email]
[v1]
Mon, 28 Jul 2025 17:55:26 UTC (3,031 KB)
[v2]
Wed, 25 Mar 2026 12:40:00 UTC (8,999 KB)
[v3]
Wed, 7 Oct 2026 18:12:04 UTC (9,841 KB)
来源：arXiv：cs.LG · arxiv.org