DNA-PPG: A Foundation Model for Photoplethysmography via Dual Neighborhood Alignment

Yang, Yizhang; Cui, Jinshi; Wu, Wenlong; Tu, Chunlong; Zhang, Yang; Lu, Junshi; Wang, Li; Gao, Guosong

doi:10.24963/ijcai.2026/777

DNA-PPG: A Foundation Model for Photoplethysmography via Dual Neighborhood Alignment

Yizhang Yang, Jinshi Cui, Wenlong Wu, Chunlong Tu, Yang Zhang, Junshi Lu, Li Wang, Guosong Gao

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. AI and Health. Pages 6984-6992.

https://doi.org/10.24963/ijcai.2026/777

Keywords

Self-supervised learning: Self-supervised learning
Remote monitoring: Remote monitoring
Health data mining: Health data mining

Abstract

Existing physiological foundation models face two limitations: rigid hard-negative sampling indiscriminately repels morphologically similar samples, distorting the natural manifold; and coarse discretization strategies sever the intrinsic continuity of physiological states, inducing precision loss. To address these challenges, we propose DNA-PPG, a novel pre-training framework anchored in Dual Neighborhood Alignment. DNA-PPG integrates the Morphology-Aware Self-Supervised Branch using Time-Frequency Soft Weighting to capture universal signal dynamics shared among diverse subjects, with the Physiological Semantic Alignment Branch that projects physiological indicators into continuous semantic space to explicitly embed precise physiological priors into the representation space. We scale the pre-training to 10.7 million PPG segments from over 8,400 subjects to ensure robust generalization. Extensive evaluations on six downstream benchmarks demonstrate that DNA-PPG significantly outperforms state-of-the-art baselines, achieving an 18% reduction in regression error and an 11.5% improvement in classification performance. These results validate DNA-PPG as a robust, universal feature extractor for diverse photoplethysmography applications.

Yizhang Yang, Jinshi Cui, Wenlong Wu, Chunlong Tu, Yang Zhang, Junshi Lu, Li Wang, and Guosong Gao. 2026. DNA-PPG: A Foundation Model for Photoplethysmography via Dual Neighborhood Alignment. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 6984–6992. https://doi.org/10.24963/ijcai.2026/777

@inproceedings{ijcai2026p777,
  title     = {DNA-PPG: A Foundation Model for Photoplethysmography via Dual Neighborhood Alignment},
  author    = {Yang, Yizhang and Cui, Jinshi and Wu, Wenlong and Tu, Chunlong and Zhang, Yang and Lu, Junshi and Wang, Li and Gao, Guosong},
  booktitle = {Proceedings of the Thirty-Fifth International Joint Conference on
               Artificial Intelligence, {IJCAI-26}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Diego Calvanese},
  pages     = {6984--6992},
  year      = {2026},
  month     = {8},
  note      = {AI and Health},
  doi       = {10.24963/ijcai.2026/777},
  url       = {https://doi.org/10.24963/ijcai.2026/777},
}

TY  - CPAPER
TI  - DNA-PPG: A Foundation Model for Photoplethysmography via Dual Neighborhood Alignment
AU  - Yang, Yizhang
AU  - Cui, Jinshi
AU  - Wu, Wenlong
AU  - Tu, Chunlong
AU  - Zhang, Yang
AU  - Lu, Junshi
AU  - Wang, Li
AU  - Gao, Guosong
T2  - Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2026
SP  - 6984
EP  - 6992
DO  - 10.24963/ijcai.2026/777
UR  - https://doi.org/10.24963/ijcai.2026/777
ER  -