首页 > AI前沿 > Transferable Evidence Reconstruction for Longitudinal Glucose Representations

Transferable Evidence Reconstruction for Longitudinal Glucose Representations

arXiv机器学习 2026-09-23 22:38 4 阅读 查看原文

Long physiological recordings contain many routine measurements, while predictive information is often concentrated in rare events, sustained burden, and recurring temporal patterns.

Masked autoencoding recovers measurements; contrastive learning aligns views.

We study self-supervision that explicitly prioritizes structured signal evidence.

We introduce transferable evidence reconstruction (TER), which constructs evidence from unlabeled recordings, fits a fresh low-capacity reader on one recording group, and requires that reader to recover the same evidence in another group without refitting.

Differentiating through this cross-group test learns representations with transferable evidence-decoding rules; the evidence guides self-supervision but is not used as a downstream feature.

For continuous glucose monitoring (CGM), an observation-aware daily encoder and clock-aware multi-day memory bind glucose level and change to recorded time while organizing up to seven days of history.

On the 14-task leaderboard, TER improves the strongest prior overall PR-AUC/ROC-AUC/Macro-F1 scores by 5.51/4.43/2.80 percentage points and sets a new best metric on 12/14 tasks.

These leaderboard gains are 2.0-2.9 times the respective gaps between the two strongest baselines.

With public pretraining data, folds, and the linear probe matched, TER outperforms our GlucoFM reproduction by 6.09/5.52/2.72 points.

Target-reader ablations, same-history controls, and cross-person readouts support the combination of structured evidence, cross-group reader fitting, and learned multi-day organization.