PhysPPG: Physics-Informed Contrastive Learning for Photoplethysmography Representation

Anonymous (ICLR 2027 double-blind)

ICLR 2027 submission· 2026
PPGFoundation Model

Summary

Temporal encoder maps PPG to latent trajectories shaped jointly by a contrastive objective and a generalized Euler–Lagrange residual (learnable kinetic/potential energies + non-conservative forces) — a low-order dynamical inductive bias without physiological labels. Frozen-encoder evaluations show benefits for BP and HR estimation on WildPPG (substantial motion / environmental variation). The learned residual also discriminates PPG vs ECG (compatibility diagnostic).

Updated: Oct 6, 2026