发表机构
Ant Group（蚂蚁集团）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出可迁移证据重建（TER）自监督方法，通过跨组读取器测试学习结构化证据解码规则，在连续血糖监测14任务上显著提升预测性能。
AI 中文摘要
长时程生理记录包含许多常规测量，而预测信息往往集中于罕见事件、持续负担和重复出现的时间模式。掩码自编码恢复测量值；对比学习对齐视图。我们研究显式优先考虑结构化信号证据的自监督方法。我们引入可迁移证据重建（TER），该方法从未标注记录中构建证据，在一个记录组上拟合一个全新的低容量读取器，并要求该读取器在不重新拟合的情况下在另一组中恢复相同证据。通过这一跨组测试进行微分，学习具有可迁移证据解码规则的表征；证据引导自监督，但不作为下游特征使用。对于连续血糖监测（CGM），一个观测感知的每日编码器和一个时钟感知的多日记忆将血糖水平和变化与记录时间绑定，同时组织长达七天的历史。在14任务排行榜上，TER将最强先前模型的总体PR-AUC/ROC-AUC/Macro-F1分数分别提升了5.51/4.43/2.80个百分点，并在12/14个任务上创下新的最佳指标。这些排行榜提升是两种最强基线之间各自差距的2.0-2.9倍。在公共预训练数据、折数和线性探针匹配的情况下，TER比我们的GlucoFM复现版本高出6.09/5.52/2.72分。目标读取器消融、同历史对照和跨人读出支持结构化证据、跨组读取器拟合和学习到的多日组织的组合。
英文摘要
Long physiological recordings contain many routine measurements, while predictive information often lies in rare events, sustained burden, and recurring patterns. These properties can be computed as label-free evidence, but directly using them as features leaves limited labeled data to separate reproducible associations from sample-specific ones. Learning to reconstruct evidence can exploit unlabeled recordings, yet joint reconstruction does not explicitly require the decoding rule to transfer across individuals. We introduce transferable evidence reconstruction (TER): a Ridge regressor fits evidence from representations in one group and predicts it in an identity-disjoint group without refitting. The transfer error trains the encoder through the differentiable fit. For continuous glucose monitoring (CGM), clock-aware encoding preserves the multi-day content and timing needed for evidence recovery. Matched interventions connect the gains to reduced fitting-group sensitivity, with structured targets improving on raw recovery. Across ten leading CGM and time-series baselines, TER sets a new best metric on 12/14 phenotype tasks and exceeds the strongest prior overall PR-AUC/ROC-AUC/Macro-F1 by 4.95/4.43/0.66 percentage points; the PR-AUC and ROC-AUC gains are $2.6\times$ and $2.2\times$ the respective gaps between the two strongest baselines. Meal-response and future-CGM studies further demonstrate predictive utility. TER thus uses meaningful signal properties to supervise not only what a representation preserves, but how reliably it can be read across individuals.
