arXiv cs.AI· Sudarshan Regmi, Nabaraj Subedi, Arvind Pillai, Yu Yvonne Wu, Yuliang Chen, Michael V. Heinz, Lisa Marsch, Nicholas C. Jacobson, Andrew Campbell·· 3 天前AI 评分24
MontageFlow：物理有效的高保真 EEG 生成模型
MontageFlow: Physically Valid High Fidelity EEG Generation
AI 导读
MontageFlow 是一种流匹配模型，通过将输出限制在满足脑电通道间线性恒等关系的信号上，实现物理有效的 EEG 生成。该模型还以从整个 EEG 窗口编码的生理状态向量为条件，该向量在生成时从潜空间先验中采样。在 3 个大规模基准上，其 TS-FID 较最接近的对手提升 1.6-3.6 倍，同时保证有效性。
正文 · 原文
Abstract:Generative modeling offers a promising solution to the scarcity of labeled clinical electroencephalography (EEG) data under strict privacy constraints. Although recent generative models report substantial improvements in generation fidelity, we show that these gains conceal a categorical failure. EEG is not an arbitrary multichannel signal: each channel records the voltage difference between two scalp electrodes. So, real recordings satisfy exact linear identities among their channels. Current generators invariably violate these identities, yet this has gone unnoticed. We therefore propose MontageFlow, a flow-matching model that enforces these identities by restricting its output to signals that satisfy them. We find that ensuring validity improves fidelity too. Furthermore, to retain the EEG characteristics that oversmoothing washes out, we also condition the model on a physiological state vector encoded from the whole EEG window. For generation, this vector is drawn from a prior fitted in latent space. Across 3 large-scale benchmarks, our model improves TS-FID by 1.6-3.6$\times$ over the closest rival while ensuring validity.
| Comments: | Code: this https URL |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.14507 [cs.AI] |
| (or arXiv:2610.14507v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.14507 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Sudarshan Regmi [view email]
[v1]
Sat, 10 Oct 2026 03:11:39 UTC (4,161 KB)
来源：arXiv cs.AI · arxiv.org