# SIGMA-PPG: Statistical-prior Informed Generative Masking Architecture for PPG Foundation Model

arXiv: https://arxiv.org/abs/2601.21031 · HTML: https://mlsanity.com/paper/2601.21031/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 45 references that are in the map.
- First posted on arXiv 28 Jan 2026.

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Training Compute-Optimal Large Language Models](https://mlsanity.com/paper/2203.15556/) (2022)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [Generating Diverse High-Fidelity Images with VQ-VAE-2](https://mlsanity.com/paper/1906.00446/) (2019)
- [Jukebox: A Generative Model for Music](https://mlsanity.com/paper/2005.00341/) (2020)
- [Large Brain Model for Learning Generic Representations with Tremendous EEG Data in BCI](https://mlsanity.com/paper/2405.18765/) (2024)
- [Stochastic Beams and Where to Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without Replacement](https://mlsanity.com/paper/1903.06059/) (2019)
- [Adversarial Masking for Self-Supervised Learning](https://mlsanity.com/paper/2201.13100/) (2022)
- [PaPaGei: Open Foundation Models for Optical Physiological Signals](https://mlsanity.com/paper/2410.20542/) (2024)
- [Ti-MAE: Self-Supervised Masked Time Series Autoencoders](https://mlsanity.com/paper/2301.08871/) (2023)
- [Pulse-PPG: An Open-Source Field-Trained PPG Foundation Model for Wearable Applications Across Lab and Field Settings](https://mlsanity.com/paper/2502.01108/) (2025)
- [HiMAE: Hierarchical Masked Autoencoders Discover Resolution-Specific Structure in Wearable Time Series](https://mlsanity.com/paper/2510.25785/) (2025)
- [GPT-PPG: A GPT-based Foundation Model for Photoplethysmography Signals](https://mlsanity.com/paper/2503.08015/) (2025)
- [Self-Supervised PPG Representation Learning Shows High Inter-Subject Variability](https://mlsanity.com/paper/2212.04902/) (2022)
- [AnyECG: Foundational Models for Multitask Cardiac Analysis in Real-World Settings](https://mlsanity.com/paper/2411.17711/) (2024)
- [Wavelet-Driven Masked Multiscale Reconstruction for PPG Foundation Models](https://mlsanity.com/paper/2601.12215/) (2026)
- [Contrastive Learning Is Not Optimal for Quasiperiodic Time Series](https://mlsanity.com/paper/2407.17073/) (2024)
- [Does Vector Quantization Fail in Spatio-Temporal Forecasting? Exploring a Differentiable Sparse Soft-Vector Quantization Approach](https://mlsanity.com/paper/2312.03406/) (2023)
- [QualityFM: a Multimodal Physiological Signal Foundation Model with Self-Distillation for Signal Quality Challenges in Critically Ill Patients](https://mlsanity.com/paper/2509.06516/) (2025)

## Built on by (most cited first, 8 of 8)

- [SP-Mind: An Autonomous Reasoning Agent for Spatial Proteomics Analysis](https://mlsanity.com/paper/2606.24235/) (2026)
- [Template Collapse and Information-Theoretic Limits in Camera rPPG Pulse Morphology Restoration](https://mlsanity.com/paper/2606.03802/) (2026)
- [When Derived Measurements Mislead: Quantifying and Mitigating LLM Over-Trust with Privileged-Modality Reliability Evidence](https://mlsanity.com/paper/2607.28421/) (2026)
- [PhysioBench: A Unified Benchmark for Physiological Signal Question Answering](https://mlsanity.com/paper/2609.20836/) (2026)
- [PPG-LM: A Photoplethysmography-Language Model with Multi-Level Clinical Alignment](https://mlsanity.com/paper/2609.33516/) (2026)
- [RAE-PPG: Duration-Grounded Retain-and-Extend Pretraining for PPG Foundation Models](https://mlsanity.com/paper/2609.36794/) (2026)
- [PulseBound: Future-Beat State Forecasting Under an Explicit Information Boundary](https://mlsanity.com/paper/2610.12010/) (2026)
- [PPG-Bench: A Unified Benchmark for PPG Foundation Models](https://mlsanity.com/paper/2610.13435/) (2026)

## Abstract (arXiv)

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.