LUNA让脑电图模型摆脱电极布局限制，高效通用且节省资源。
LUNA: Efficient and Topology-Agnostic Foundation Model for EEG Signal Analysis
- 用可学习查询和交叉注意力将不同电极布局的脑电信号统一到固定大小的隐空间。
- 在多个任务上表现顶尖，如TUAR数据集达0.921 AUROC，计算量减少300倍。
- 适合脑电分析、医疗智能等需要跨设备通用性的研究者使用。
脑电图（EEG）为非侵入性观测大脑活动提供了窗口，但构建大规模模型受限于电极拓扑异质性：各公开数据集定义了不同的电极布局，阻碍泛化能力。我们提出LUNA（潜空间统一网络架构），一种自监督基础模型，能兼容不同电极几何结构，且计算量随通道数线性增长而非二次增长。LUNA通过学习查询与交叉注意力，将多通道脑电信号压缩至固定大小的拓扑无关隐空间。下游变压器模块仅在该隐表示上以分块时间自注意力方式运行，实现计算与电极数量解耦。在超过21,000小时原始脑电数据（涵盖TUEG和Siena多个导联系统）上预训练，采用掩码片段重建目标。模型在四项下游任务中有效迁移：异常检测、伪迹去除、慢波分类和情绪识别。在多个基准测试中表现优异，如在TUAR和TUSL上达到领先水平，其中TUAR上达到0.921 AUROC；同时计算量降低300倍，显存使用减少最多10倍。这些优势在所有评估的电极配置下均保持一致。代码已开源。
原文摘要 · Abstract (English)
Electroencephalography (EEG) offers a non-invasive lens into human brain activity, but building large-scale models is hampered by topological heterogeneity: each public EEG data defines its own electrode layout, limiting generalization. We introduce LUNA (Latent Unified Network Architecture), a self-supervised foundation model that reconciles disparate electrode geometries while scaling linearly -- not quadratically -- with channel count. LUNA compresses multi-channel EEG into a fixed-size, topology-agnostic latent space via learned queries and cross-attention. Downstream transformer blocks then operate exclusively on this latent representation using patch-wise temporal self-attention, decoupling computation from electrode count. Pre-trained on TUEG and Siena (over 21,000 hours of raw EEG across diverse montages) using a masked-patch reconstruction objective, LUNA transfers effectively to four downstream tasks: abnormality detection, artifact rejection, slowing classification, and emotion recognition. It demonstrates highly competitive performance across several benchmarks, achieving state-of-the-art results on TUAR and TUSL, e.g., 0.921 AUROC on TUAR, while reducing FLOPs by 300x and trimming GPU memory use by up to 10x. Critically, these gains are consistent across all evaluated electrode configurations. Code is available at https://github.com/pulp-bio/BioFoundation
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。