SIGMA-PPG: Statistical-prior Informed Generative Masking Architecture for PPG Foundation Model
This addresses the problem of noisy and redundant PPG signal analysis for healthcare and monitoring applications, representing a novel method for a known bottleneck.
The paper tackles the challenge of building foundation models for photoplethysmography (PPG) signals, which suffer from redundancy and noise, by proposing SIGMA-PPG, a generative model that uses statistical priors and adversarial masking to prevent overfitting. It achieves superior average performance compared to five state-of-the-art baselines across 12 diverse downstream tasks, pre-trained on over 120,000 hours of data.
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.