arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2512.00239cs.LGstat.ML
收藏

生理时间序列的自监督动力系统表示

Self-Supervised Dynamical System Representations for Physiological Time-Series

University of California, Berkeley(加州大学伯克利分校);Stanford University(斯坦福大学)

Yenho Chen, Maxwell A. Xu, James M. Rehg, Christopher J. Rozell

AI总结:

提出PULSE框架,利用动力系统生成模型的信息结构,通过跨重建预训练目标提取共享系统参数信息,丢弃样本特异性噪声,提升生理时间序列的表示学习效果。

摘要:

自监督学习(SSL)对生理时间序列的有效性取决于预训练目标在过滤掉无关噪声的同时保留关于潜在生理状态信息的能力。然而,现有策略由于依赖启发式原则或约束较差的生成任务而受到限制。为解决这一限制,我们提出一个预训练框架,该框架利用跨多个时间序列的动力系统生成模型的信息结构。该框架揭示了我们的关键见解:通过提取与跨相似时间序列样本共享的系统参数相关的生成变量信息,可以高效捕获类别身份,而应丢弃单个样本特有的噪声。基于这一见解,我们提出PULSE,一种基于跨重建的生理时间序列数据集预训练目标,它在丢弃不可迁移的样本特异性信息的同时显式提取系统信息。我们建立了提供系统信息恢复充分条件的理论,并通过合成动力系统实验进行了实证验证。此外,我们将我们的方法应用于多种真实世界数据集,证明PULSE学习到的表示能够广泛区分语义类别、提高标签效率并改进迁移学习。

英文摘要:

The effectiveness of self-supervised learning (SSL) for physiological time series depends on the ability of a pretraining objective to preserve information about the underlying physiological state while filtering out unrelated noise. However, existing strategies are limited due to reliance on heuristic principles or poorly constrained generative tasks. To address this limitation, we propose a pretraining framework that exploits the information structure of a dynamical systems generative model across multiple time-series. This framework reveals our key insight that class identity can be efficiently captured by extracting information about the generative variables related to the system parameters shared across similar time series samples, while noise unique to individual samples should be discarded. Building on this insight, we propose PULSE, a cross-reconstruction-based pretraining objective for physiological time series datasets that explicitly extracts system information while discarding non-transferrable sample-specific ones. We establish theory that provides sufficient conditions for the system information to be recovered, and empirically validate it using a synthetic dynamical systems experiment. Furthermore, we apply our method to diverse real-world datasets, demonstrating that PULSE learns representations that can broadly distinguish semantic classes, increase label efficiency, and improve transfer learning.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑