Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.21031 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908795784921088 |
|---|---|
| author | Guo, Zongheng Chen, Tao Jiao, Yang Pan, Yi Hu, Xiao Ferrario, Manuela |
| author_facet | Guo, Zongheng Chen, Tao Jiao, Yang Pan, Yi Hu, Xiao Ferrario, Manuela |
| contents | Current foundation model for photoplethysmography (PPG) signals is challenged by the intrinsic redundancy and noise of the signal. Standard masked modeling often yields trivial solutions while contrastive methods lack morphological precision. To address these limitations, we propose a Statistical-prior Informed Generative Masking Architecture (SIGMA-PPG), a generative foundation model featuring a Prior-Guided Adversarial Masking mechanism, where a reinforcement learning-driven teacher leverages statistical priors to create challenging learning paths that prevent overfitting to noise. We also incorporate a semantic consistency constraint via vector quantization to ensure that physiologically identical waveforms (even those altered by recording artifacts or minor perturbations) map to shared indices. This enhances codebook semantic density and eliminates redundant feature structures. Pre-trained on over 120,000 hours of data, SIGMA-PPG achieves superior average performance compared to five state-of-the-art baselines across 12 diverse downstream tasks. The code is available at https://github.com/ZonghengGuo/SigmaPPG. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_21031 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SIGMA-PPG: Statistical-prior Informed Generative Masking Architecture for PPG Foundation Model Guo, Zongheng Chen, Tao Jiao, Yang Pan, Yi Hu, Xiao Ferrario, Manuela Machine Learning Artificial Intelligence J.3 Current foundation model for photoplethysmography (PPG) signals is challenged by the intrinsic redundancy and noise of the signal. Standard masked modeling often yields trivial solutions while contrastive methods lack morphological precision. To address these limitations, we propose a Statistical-prior Informed Generative Masking Architecture (SIGMA-PPG), a generative foundation model featuring a Prior-Guided Adversarial Masking mechanism, where a reinforcement learning-driven teacher leverages statistical priors to create challenging learning paths that prevent overfitting to noise. We also incorporate a semantic consistency constraint via vector quantization to ensure that physiologically identical waveforms (even those altered by recording artifacts or minor perturbations) map to shared indices. This enhances codebook semantic density and eliminates redundant feature structures. Pre-trained on over 120,000 hours of data, SIGMA-PPG achieves superior average performance compared to five state-of-the-art baselines across 12 diverse downstream tasks. The code is available at https://github.com/ZonghengGuo/SigmaPPG. |
| title | SIGMA-PPG: Statistical-prior Informed Generative Masking Architecture for PPG Foundation Model |
| topic | Machine Learning Artificial Intelligence J.3 |
| url | https://arxiv.org/abs/2601.21031 |