Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Huang, Zhengdong, Xie, Zicheng, Tian, Wentao, Liu, Jingyu, Dong, Lunhong, Yang, Peng
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2508.21785
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912922090864640
author Huang, Zhengdong
Xie, Zicheng
Tian, Wentao
Liu, Jingyu
Dong, Lunhong
Yang, Peng
author_facet Huang, Zhengdong
Xie, Zicheng
Tian, Wentao
Liu, Jingyu
Dong, Lunhong
Yang, Peng
contents Heart rate prediction is vital for personalized health monitoring and fitness, while it frequently faces a critical challenge in real-world deployment: data heterogeneity. We classify it in two key dimensions: source heterogeneity from fragmented device markets with varying feature sets, and user heterogeneity reflecting distinct physiological patterns across individuals and activities. Existing methods either discard device-specific information, or fail to model user-specific differences, limiting their real-world performance. To address this, we propose a framework that learns latent representations agnostic to both heterogeneity,enabling downstream predictors to work consistently under heterogeneous data patterns. Specifically, we introduce a random feature dropout strategy to handle source heterogeneity, making the model robust to various feature sets. To manage user heterogeneity, we employ a history-aware attention module to capture long-term physiological traits and use a contrastive learning objective to build a discriminative representation space. To reflect the heterogeneous nature of real-world data, we created a new benchmark dataset, PARROTAO. Evaluations on both PARROTAO and the public FitRec dataset show that our model significantly outperforms existing baselines by 17.5% and 10.4% in terms of test MSE, respectively. Furthermore, analysis of the learned representations demonstrates their strong discriminative power,and two downstream application tasks confirm the practical value of our model.
format Preprint
id arxiv_https___arxiv_org_abs_2508_21785
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning Unified Representations from Heterogeneous Data for Robust Heart Rate Modeling
Huang, Zhengdong
Xie, Zicheng
Tian, Wentao
Liu, Jingyu
Dong, Lunhong
Yang, Peng
Machine Learning
Computer Vision and Pattern Recognition
Heart rate prediction is vital for personalized health monitoring and fitness, while it frequently faces a critical challenge in real-world deployment: data heterogeneity. We classify it in two key dimensions: source heterogeneity from fragmented device markets with varying feature sets, and user heterogeneity reflecting distinct physiological patterns across individuals and activities. Existing methods either discard device-specific information, or fail to model user-specific differences, limiting their real-world performance. To address this, we propose a framework that learns latent representations agnostic to both heterogeneity,enabling downstream predictors to work consistently under heterogeneous data patterns. Specifically, we introduce a random feature dropout strategy to handle source heterogeneity, making the model robust to various feature sets. To manage user heterogeneity, we employ a history-aware attention module to capture long-term physiological traits and use a contrastive learning objective to build a discriminative representation space. To reflect the heterogeneous nature of real-world data, we created a new benchmark dataset, PARROTAO. Evaluations on both PARROTAO and the public FitRec dataset show that our model significantly outperforms existing baselines by 17.5% and 10.4% in terms of test MSE, respectively. Furthermore, analysis of the learned representations demonstrates their strong discriminative power,and two downstream application tasks confirm the practical value of our model.
title Learning Unified Representations from Heterogeneous Data for Robust Heart Rate Modeling
topic Machine Learning
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.21785