发表机构
Zhejiang University; Shanghai Innovation Institute; Fudan University; Huazhong University of Science and Technology（浙江大学; 上海创新研究院; 复旦大学; 华中科技大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出生成式基础模型SOTER，融合跨通道耦合、频谱引导专家与连续时间潜演化，在可穿戴生理信号上实现最优零样本预测、分类与插补性能。
AI 中文摘要
时间序列基础模型已展现出强大的跨域迁移能力，但其常见的架构假设与可穿戴生理信号（多通道、不规则采样、含噪声、由跨越不同频谱尺度的耦合连续时间动力学支配）并不匹配。我们提出SOTER，一个面向可穿戴生理时间序列的生成式基础模型，在单一预训练框架内统一了跨通道耦合、频谱引导的专家特化和连续时间潜演化。SOTER结合了建模信号间依赖关系的空间特征感知骨干网络、通过可检查的非学习规则将表示路由到与固定频谱带相关联的专家的功率谱密度（PSD）引导的混合专家层，以及支持任意时间戳预测和插补的神经受控微分方程解码器。我们在来自五个公共生理数据集的2260亿个时间点上预训练SOTER，并在可穿戴基准上评估同一预训练模型的分布外零样本预测、冻结编码器线性探测分类和连续时间插补。SOTER在零样本预测中于6个数据集中的4个取得最佳RMSE，在6个中的5个取得最佳MAE，在分类中取得最高平均宏AUROC，并在75%缺失率下于全部六个数据集取得最低插补误差。它还对加性采集噪声保持鲁棒，即使在最强污染下也能匹配或超越在干净输入上评估的基线。这些结果表明，面向可穿戴生理学的领域特化基础模型受益于联合建模通道结构、频谱尺度和连续时间动力学。
英文摘要
Time-series foundation models have demonstrated strong cross-domain transfer, yet their common architectural assumptions remain poorly aligned with wearable physiological signals, which are multichannel, irregularly sampled, noisy, and governed by coupled continuous-time dynamics spanning distinct spectral scales. We present SOTER, a generative foundation model for wearable physiological time series that unifies cross-channel coupling, spectrum-guided expert specialization, and continuous-time latent evolution within a single pre-training framework. SOTER combines a spatial feature-aware backbone that models inter-signal dependencies, a power spectral density (PSD)-guided mixture-of-experts layer that routes representations to experts associated with fixed spectral bands through an inspectable, non-learned rule, and a neural controlled differential equation decoder that supports prediction and imputation at arbitrary timestamps. We pre-train SOTER on 226 billion time points from five public physiological datasets and evaluate the same pre-trained model across out-of-distribution zero-shot forecasting, frozen-encoder linear-probe classification, and continuous-time imputation on wearable benchmarks. SOTER achieves the best RMSE on 4 of 6 datasets and the best MAE on 5 of 6 in zero-shot forecasting, the highest average Macro-AUROC in classification, and the lowest imputation error on all six datasets at 75% missingness. It further remains robust to additive acquisition noise, matching or surpassing baselines evaluated on clean inputs even under the strongest corruption. These results indicate that domain-specialized foundation models for wearable physiology benefit from jointly modeling channel structure, spectral scale, and continuous-time dynamics.
