AI 中文总结
针对非规则时间序列预测的现有方法缺陷，提出WrapFlow连续时间建模框架，通过连续时间分词与无模拟残差流匹配训练范式，在真实数据集上实现最优预测性能。
AI 中文摘要
非规则多变量时间序列广泛应用于医疗监护、人体活动识别和环境感知等场景，其核心挑战源于异步观测、非均匀采样间隔，且时间模式本身携带关键动态信息。现有方法要么依赖基于离散化的预处理（如插值、补全或聚合），这会破坏底层连续时间语义；要么采用基于常微分方程（ODE）的框架进行连续时间建模，这类框架通常需要专用架构，且因数值求解器会产生大量计算开销。为解决这些局限，我们提出WrapFlow——一种用于非规则时间序列预测的连续时间建模框架。在输入侧，WrapFlow引入连续时间分词，直接编码原始观测事件，并通过感知间隔的分词显式建模未观测的长间隔；生成的连续时间分词随后由标准Transformer主干处理，以捕捉长程时间依赖关系。在输出侧，我们开发了无模拟训练范式用于残差流匹配，该范式学习基预测周围的条件残差向量场，同时避免训练期间的数值求解器模拟与反向传播。此设计在推理时仅需少量固定的展开步骤即可实现高质量连续预测。在多个真实世界数据集上开展的大量实验表明，WrapFlow达到了最优性能。
英文摘要
Irregular multivariate time series are widely encountered in applications such as healthcare monitoring, human activity recognition, and environmental sensing. Their core challenges stem from asynchronous observations, non-uniform sampling intervals, and the fact that temporal patterns themselves carry critical dynamic information. Existing approaches either rely on discretization-based preprocessing (e.g., interpolation, imputation, or aggregation), which disrupts the underlying continuous-time semantics, or adopt continuous-time modeling via ODE-based frameworks, which typically require specialized architectures and incur substantial computational overhead due to numerical solvers. To address these limitations, we propose WrapFlow, a continuous-time modeling framework for irregular time series forecasting. On the input side, WrapFlow introduces Continuous-Time Tokenization, which directly encodes raw observation events and explicitly models long unobserved intervals via gap-aware tokens. The resulting continuous-time tokens are then processed by a standard Transformer backbone to capture long-range temporal dependencies. On the output side, we develop a simulation-free training paradigm for Residual Flow Matching, which learns conditional residual vector fields around base predictions while avoiding numerical-solver simulation and backpropagation during training. This design enables high-quality continuous forecasting using only a small number of fixed rollout steps at inference. Extensive experiments on multiple real-world datasets demonstrate that WrapFlow achieves state-of-the-art performance.
Comments13 pages, 5 figures
