arXiv：cs.LG· Shaocong Wang, Tong Liu, Yihan Li, Ming Li, Kairui Wen, Pei Yang, Wenqi Ji, Minjing Yu, Yong-Jin Liu·· 5 小时前AI 评分27
EEGDM：用潜在扩散模型学习 EEG 表征
EEGDM: Learning EEG Representation with Latent Diffusion Model
AI 导读
EEGDM 是一个自监督框架，用潜在扩散模型生成 EEG 信号作为训练目标，替代传统掩码重建。它通过 EEG 编码器将原始信号及其通道增强压缩为紧凑表征，作为条件引导扩散去噪，并联合优化编码器与扩散模型。
正文
Abstract:Recent advances in self-supervised learning for EEG representation have largely relied on masked reconstruction, where models are trained to recover randomly masked signal segments. While effective at modeling local dependencies, the training objective of masked reconstruction does not compel the model to capture global generative constraints essential for characterizing neural activity. To address this limitation, we propose EEGDM, a novel self-supervised framework that leverages latent diffusion models to generate EEG signals as an objective. Unlike masked reconstruction, diffusion-based generation progressively denoises signals from noise to realism, compelling the model to capture holistic temporal patterns and cross-channel relationships. Specifically, EEGDM incorporates an EEG encoder that distills raw signals and their channel augmentations into a compact representation, which serves as conditional information to guide the diffusion denoising process, thereby enabling the encoder and diffusion model to be jointly optimized through the generative objective. This design endows EEGDM with a compact latent space, which not only offers ample control over the generative process but also can be leveraged for downstream tasks. Experimental results show that EEGDM (1) reconstructs high-quality EEG signals, (2) learns robust representations, and (3) achieves competitive performance across diverse downstream tasks, thus exploring a new direction for self-supervised EEG representation learning.
| Comments: | This paper was accepted by IEEE Transactions on Biomedical Engineering |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2508.20705 [cs.LG] |
| (or arXiv:2508.20705v5 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2508.20705 arXiv-issued DOI via DataCite |
|
| Journal reference: | IEEE Transactions on Biomedical Engineering, 2026 |
| Related DOI: | https://doi.org/10.1109/TBME.2026.3740193
DOI(s) linking to related resources |
Submission history
From: Tong Liu [view email]
[v1]
Thu, 28 Aug 2025 12:23:28 UTC (473 KB)
[v2]
Fri, 19 Dec 2025 02:47:26 UTC (677 KB)
[v3]
Thu, 16 Apr 2026 01:44:53 UTC (674 KB)
[v4]
Sun, 30 Aug 2026 12:43:19 UTC (668 KB)
[v5]
Fri, 2 Oct 2026 11:59:16 UTC (668 KB)
来源：arXiv：cs.LG · arxiv.org