构建可同时理解整晚睡眠结构与微小信号特征的通用睡眠模型
SleepMaMi: A Universal Sleep Foundation Model for Integrating Macro- and Micro-structures
- 采用分层双编码器架构，分别建模整晚时序与短时生物信号特征
- 在超过15万小时的睡眠数据上预训练，跨任务表现优于或媲美现有模型
- 适合临床睡眠分析、少样本迁移学习场景，尤其关注全夜睡眠结构
尽管统一基础模型已在多个深度学习领域引发变革，睡眠医学仍主要依赖针对特定任务的模型，聚焦局部微结构特征。此类方法常忽略多模态的多导睡眠图（PSG）丰富上下文，也难以捕捉整晚睡眠的全局宏观结构。为此，我们提出 SleepMaMi，一个专为睡眠设计的基础模型，能同时掌握小时级睡眠架构与细粒度信号形态。其框架采用分层双编码器：宏编码器建模整晚时序依赖，微观编码器提取生物信号的短期特征。宏编码器通过基于人口统计信息的对比学习训练，将整晚睡眠模式与年龄、性别、体重指数等客观元数据对齐，优化全局表示；微观编码器则结合掩码自编码器（MAE）与多模态对比目标进行优化。在超过20,000份PSG记录（总计158,000小时）上预训练后，SleepMaMi 在多样下游任务中表现优异，展现出卓越的泛化能力与标签高效适应性，适用于临床睡眠分析。
原文摘要 · Abstract (English)
While the shift toward unified foundation models has revolutionized many deep learning domains, sleep medicine remains largely restricted to task-specific models that focus on localized micro-structure features. These approaches often neglect the rich, multi-modal context of Polysomnography (PSG) and fail to capture the global macro-structure of a full night's sleep. To address this, we introduce SleepMaMi , a Sleep Foundation Model engineered to master both hour-long sleep architectures and fine-grained signal morphologies. Our framework utilizes a hierarchical dual-encoder design: a Macro-Encoder to model full-night temporal dependencies and a Micro-Encoder to capture short-term characteristics from biosignals. Macro-Encoder is trained via Demographic-Guided Contrastive Learning, which aligns overnight sleep patterns with objective subject metadata, such as age, sex and BMI to refine global representations. Micro-Encoder is optimized via a hybrid Masked Autoencoder (MAE) and multi-modal contrastive objective. Pre-trained on a massive corpus of $>$20,000 PSG recordings (158K hours),SleepMaMi outperforms or matches state-of-the-art existing foundation models across a diverse suite of downstream tasks, demonstrating superior generalizability and label-efficient adaptation for clinical sleep analysis.
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。