用知识蒸馏让大模型变小，实现在可穿戴设备上高效分析心率和房颤
PPG-Distill: Efficient Photoplethysmography Signals Analysis via Foundation Model Distillation
- 通过预测、特征和片段级蒸馏，同时保留全局与局部信息
- 心率估计与房颤检测性能提升最高21.8%，推理速度提升7倍
- 适合资源受限的可穿戴健康设备部署，尤其关注实时生理信号分析
光电容积脉搏波描记法（PPG）广泛用于可穿戴健康监测，但大型PPG基础模型难以在资源受限设备上部署。本文提出PPG-Distill，一种知识蒸馏框架，通过预测、特征和片段级蒸馏，传递全局与局部知识。该方法引入形态学蒸馏以保留局部波形模式，以及节奏蒸馏以捕捉片段间的时序结构。在心率估计与房颤检测任务中，PPG-Distill使学生模型性能提升最高达21.8%，推理速度加快7倍，内存占用减少19倍，显著提升可穿戴设备上的高效PPG分析能力。
原文摘要 · Abstract (English)
Photoplethysmography (PPG) is widely used in wearable health monitoring, yet large PPG foundation models remain difficult to deploy on resource-limited devices. We present PPG-Distill, a knowledge distillation framework that transfers both global and local knowledge through prediction-, feature-, and patch-level distillation. PPG-Distill incorporates morphology distillation to preserve local waveform patterns and rhythm distillation to capture inter-patch temporal structures. On heart rate estimation and atrial fibrillation detection, PPG-Distill improves student performance by up to 21.8% while achieving 7X faster inference and reducing memory usage by 19X, enabling efficient PPG analysis on wearables.
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。