Towards Characterizing Knowledge Distillation of PPG Heart Rate Estimation Models

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Arora, Kanav, Narayanswamy, Girish, Patel, Shwetak, Li, Richard
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918238748672000
author Arora, Kanav
Narayanswamy, Girish
Patel, Shwetak
Li, Richard
author_facet Arora, Kanav
Narayanswamy, Girish
Patel, Shwetak
Li, Richard
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_18829
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards Characterizing Knowledge Distillation of PPG Heart Rate Estimation Models
Arora, Kanav
Narayanswamy, Girish
Patel, Shwetak
Li, Richard
Machine Learning
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.
title Towards Characterizing Knowledge Distillation of PPG Heart Rate Estimation Models
topic Machine Learning
url https://arxiv.org/abs/2511.18829