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.
@article{arxiv.2509.19215,
title = {PPG-Distill: Efficient Photoplethysmography Signals Analysis via Foundation Model Distillation},
author = {Juntong Ni and Saurabh Kataria and Shengpu Tang and Carl Yang and Xiao Hu and Wei Jin},
journal= {arXiv preprint arXiv:2509.19215},
year = {2025}
}
Comments
Accepted at NeurIPS 2025 TS4H, we release our code publicly at https://github.com/LingFengGold/PPG-Distill