arXiv cs.LG + cs.RO + cs.HC· Yi Ding, Muyun Jiang, Weibang Jiang, Shuailei Zhang, Xinliang Zhou, Chenyu Liu, Shanglin Li, Yong Li, Cuntai Guan·· 1 天前精选AI 评分60
BrainPro：按实验范式条件化预训练的大规模 EEG 模型
BrainPro: Process-conditioned Pretraining with Topographic Retrieval for Large EEG Models
AI 导读
研究团队提出 BrainPro，一个将电极布局映射到统一通道-脑区模板、并按实验范式线索条件化分支激活与掩码重建的 EEG 自监督预训练框架。该方法在 9 个公开 BCI 基准上取得较强表现，消融与通道缺失分析显示地形检索与过程条件化表示学习共同提升解码效果。论文已被 NeurIPS 2026 接收，代码已公开。
推荐理由
论文提出按实验范式条件化的 EEG 预训练框架，并在 9 个公开 BCI 基准上做了对比与消融，可供关注 EEG 大模型路线的人参考。
正文 · 原文
Abstract:EEG foundation models are pretrained on heterogeneous corpora, but two challenges remain underexplored: (1) experimental protocols provide mental-process cues that are rarely used in masked pretraining, and (2) electrode montages vary across datasets, making spatial representations montage-dependent. Existing methods typically learn a single general-purpose representation and model spatial structure implicitly, limiting their ability to exploit process-related information under montage heterogeneity. We introduce BrainPro, a process-conditioned self-supervised pretraining framework that couples topographic retrieval with shared and process-associated representation learning. BrainPro maps dataset-specific montages to a universal channel-region template and retrieves channel- and region-level spatial filters to form a topographically aligned spatial basis. Over this basis, BrainPro learns a shared encoder for general EEG structure and additional affective, motor-related, and auxiliary residual branches for process-associated variation. Protocol-derived mental-process cues condition branch activation and region-weighted masked reconstruction, incorporating topographic spatial priors and process information. Across nine public BCI benchmarks, BrainPro achieves strong performance among evaluated baselines. Ablations, channel-drop analysis, encoder-configuration studies, and spatial-filter visualizations suggest that topographic retrieval and process-conditioned representation learning jointly improve EEG decoding. Our code is available at this https URL.
| Comments: | Accepted by NeurIPS 2026 |
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2509.22050 [cs.LG] |
| (or arXiv:2509.22050v3 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2509.22050 arXiv-issued DOI via DataCite |
Submission history
From: Yi Ding [view email]
[v1]
Fri, 26 Sep 2025 08:34:04 UTC (4,479 KB)
[v2]
Thu, 11 Jun 2026 15:32:52 UTC (5,006 KB)
[v3]
Wed, 21 Oct 2026 09:39:44 UTC (4,886 KB)
来源：arXiv cs.LG + cs.RO + cs.HC · arxiv.org