ChatPPG.
Paper

P2E-VQ: ECG-linked representation augmentation for PPG via discrete patch retrieval

Zhongli Wu, Zhuangzhi Gao, He Zhao, Feixiang Zhou, Fu Wang, Jinru Ding +5 more
arXiv preprint2026PPGECG
arXiv Cite
PreprintFirst posted: Jul 31, 2026Added to atlas: Oct 11, 2026Source
Citations—Not available
GitHub stars—Not available
HF downloads—Not available

Activity counts measure attention, not model quality. Missing counts are unknown. Publication status follows the linked source; a listed venue alone does not confirm peer review.

P2E-VQ helps PPG models pick up cardiac information that normally needs ECG. It turns PPG patches into discrete tokens and retrieves ECG-linked information from a memory bank built from training data, instead of reconstructing ECG waveforms. Across five datasets and six tasks it beat pretrained baselines under frozen linear probing.

  • Signals: PPG (ECG-linked retrieval)
  • Evaluation: 5 datasets, 6 tasks
At a glance
Venue
arXiv preprint
Published
2026
DOI
Not reported
arXiv
2608.14656 (opens in a new tab)
PMID
Not reported
Licence
Not reported
Signals
PPGECG
Form factor
Not reported
Subjects
Not reported
Code
Not reported
Added
Oct 11, 2026

Abstract

Photoplethysmography (PPG) is widely used in consumer wearables because of its low cost and ease of acquisition. However, unlike electrocardiography (ECG), PPG measures peripheral pulse dynamics rather than cardiac electrical activity, limiting its ability to predict cardiac conditions that rely on ECG-specific morphological cues. Existing methods attempt to bridge this gap by reconstructing ECG signals from PPG signals. However, this inverse mapping is inherently ill-posed, and faithful waveform reconstruction does not necessarily translate into improved downstream performance. To address this challenge, we propose P2E-VQ, a retrieval-augmented framework that replaces ECG waveform reconstruction with ECG-linked representation retrieval. Specifically, P2E-VQ converts PPG patches into discrete tokens and retrieves ECG-linked information from a memory bank constructed exclusively from the training data. This process augments PPG representations while requiring only PPG signals during inference. Extensive experiments on five public datasets covering six downstream tasks, including clinical endpoint prediction and affective state recognition, demonstrate that P2E-VQ consistently outperforms pretrained baselines under a unified frozen-feature linear-probing protocol.

Verbatim fromarXiv· arXiv metadata (abstracts are released under CC0)

P2E-VQ: ECG-linked representation augmentation for PPG via discrete patch retrieval: ChatPPG research summary card

How it works

How Method works: Setup → Method → ResultSetup: Signals (PPG (ECG-linked retrieval)). Method: Method, discrete patch tokens + retrieval memory bank. Result: Evaluation (5 datasets, 6 tasks).SetupSignals: PPG (ECG-linked retrieval)SignalsPPG (ECG-linked retrieval)MethodMethoddiscrete patch tokens + retrieval…ResultEvaluation: 5 datasets, 6 tasksEvaluation5 datasets, 6 tasks
Method
discrete patch tokens + retrieval memory bank

Cite

@article{p2evqecglinkedrepresenta2026,
  title = {{P2E-VQ: ECG-linked representation augmentation for PPG via discrete patch retrieval}},
  author = {Zhongli Wu and Zhuangzhi Gao and He Zhao and Feixiang Zhou and Fu Wang and Jinru Ding and Yuankai Wang and Hongyi Qin and Gregory Y. H. Lip and Bil Kirmani and Yalin Zheng},
  year = {2026},
  journal = {arXiv preprint},
  eprint = {2608.14656}
}

History

  1. Added to the ChatPPG research hub

More on ChatPPG