RAMP: Reliability Adaptive Masking for Pretraining Noisy Multimodal Physiological Signals

Anonymous (ICLR 2027 double-blind)

ICLR 2027 submission· 2026
PPGECGEEGIMUFoundation Model

Summary

Profiles each ECG and PPG patch by quality, corruption type and spectral degradation; a compact Reliability Policy Network jointly selects masking threshold, temporal granularity and cross-modal fusion weights via differentiable relaxations, reconstructing degraded regions from cleaner temporal / cross-modal context. On MIMIC-III and VitalDB, pretraining RMSE −16% vs the strongest fixed-policy baseline (largest gains under asymmetric modality corruption). Pretrained encoder: 93.9 / 93.9 / 93.2% mean ACC / macro-F1 / ROC-AUC across six downstream benchmarks spanning ECG, PPG, EEG and accelerometry (reproduced baselines, unified protocol).

Updated: Oct 6, 2026