arXiv：cs.AI· Sudarshan Regmi, Nabaraj Subedi, Arvind Pillai, Yu Yvonne Wu, Yuliang Chen, Michael V. Heinz, Lisa Marsch, Nicholas C. Jacobson, Andrew Campbell·· 16 小时前
MontageFlow：物理有效的高保真 EEG 生成
MontageFlow: Physically Valid High Fidelity EEG Generation
AI 导读
MontageFlow 是一个流匹配模型，通过把输出限制在满足各通道线性恒等式的信号上，解决现有 EEG 生成器普遍违反电极电压差恒等式的问题。该模型还以从整个 EEG 窗口编码的生理状态向量为条件，该向量在生成时从隐空间拟合的先验中采样。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
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