Score: 1

Towards Characterizing Knowledge Distillation of PPG Heart Rate Estimation Models

Published: November 24, 2025 | arXiv ID: 2511.18829v1

By: Kanav Arora , Girish Narayanswamy , Shwetak Patel and more

BigTech Affiliations: University of Washington

Potential Business Impact:

Makes smartwatches accurately track heart rates.

Business Areas:
Predictive Analytics Artificial Intelligence, Data and Analytics, Software

Heart rate estimation from photoplethysmography (PPG) signals generated by wearable devices such as smartwatches and fitness trackers has significant implications for the health and well-being of individuals. Although prior work has demonstrated deep learning models with strong performance in the heart rate estimation task, in order to deploy these models on wearable devices, these models must also adhere to strict memory and latency constraints. In this work, we explore and characterize how large pre-trained PPG models may be distilled to smaller models appropriate for real-time inference on the edge. We evaluate four distillation strategies through comprehensive sweeps of teacher and student model capacities: (1) hard distillation, (2) soft distillation, (3) decoupled knowledge distillation (DKD), and (4) feature distillation. We present a characterization of the resulting scaling laws describing the relationship between model size and performance. This early investigation lays the groundwork for practical and predictable methods for building edge-deployable models for physiological sensing.

Country of Origin
🇺🇸 United States

Page Count
6 pages

Category
Computer Science:
Machine Learning (CS)