PPG-Distill: Efficient Photoplethysmography Signals Analysis via Foundation Model Distillation
This work addresses efficiency challenges in health monitoring for wearable device users, though it is incremental as it builds on existing distillation methods.
The paper tackled the problem of deploying large photoplethysmography (PPG) foundation models on resource-limited wearable devices by proposing PPG-Distill, a knowledge distillation framework that improved student model performance by up to 21.8% for tasks like heart rate estimation and atrial fibrillation detection.
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.