arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2511.14488cs.LGcs.AI
收藏

面向稳定且结构化时间序列生成的扰动感知流匹配方法

Towards Stable and Structured Time Series Generation with Perturbation-Aware Flow Matching

State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China(认知智能国家重点实验室,中国科学技术大学);The First Affiliated Hospital of University of Science and Technology of China(中国科学技术大学第一附属医院)

Jintao Zhang, Mingyue Cheng, Zirui Liu, Xianquan Wang, Yitong Zhou, Qi Liu

AI总结:

针对局部扰动导致的时间异质性使时间序列生成结构不一致的问题,提出PAFM框架,通过扰动引导训练、双路径速度场和流路由混合专家解码器,在无条件和条件生成任务中持续优于强基线。

摘要:

时间序列生成对广泛应用至关重要,极大支持下游分析与决策任务。然而,局部扰动引发的固有时间异质性为生成结构一致的时间序列带来重大挑战。尽管流匹配通过轨迹级监督建模时间动态提供了有前景的范式,但由于使用全局共享参数将速度场限制为统一表示,无法充分捕捉扰动时间序列中的突变。为解决这些局限,我们引入PAFM(扰动感知流匹配)框架,通过建模扰动轨迹确保生成稳定且结构一致的时间序列。该框架包含扰动引导训练以模拟局部干扰,并利用双路径速度场捕捉扰动下的轨迹偏差,实现对扰动行为的精细建模以增强结构连贯性。为进一步提高对轨迹扰动的敏感性并增强表达能力,带流路由的混合专家解码器可根据不同轨迹动态分配建模能力。在无条件和条件生成任务上的大量实验表明,PAFM持续优于强基线。代码可在https://anonymous.4open.science/r/PAFM-03B2获取。

英文摘要:

Time series generation is critical for a wide range of applications, which greatly supports downstream analytical and decision-making tasks. However, the inherent temporal heterogeneous induced by localized perturbations present significant challenges for generating structurally consistent time series. While flow matching provides a promising paradigm by modeling temporal dynamics through trajectory-level supervision, it fails to adequately capture abrupt transitions in perturbed time series, as the use of globally shared parameters constrains the velocity field to a unified representation. To address these limitations, we introduce \textbf{PAFM}, a \textbf{P}erturbation-\textbf{A}ware \textbf{F}low \textbf{M}atching framework that models perturbed trajectories to ensure stable and structurally consistent time series generation. The framework incorporates perturbation-guided training to simulate localized disturbances and leverages a dual-path velocity field to capture trajectory deviations under perturbation, enabling refined modeling of perturbed behavior to enhance the structural coherence. In order to further improve sensitivity to trajectory perturbations while enhancing expressiveness, a mixture-of-experts decoder with flow routing dynamically allocates modeling capacity in response to different trajectory dynamics. Extensive experiments on both unconditional and conditional generation tasks demonstrate that PAFM consistently outperforms strong baselines. Code is available at https://anonymous.4open.science/r/PAFM-03B2.

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。

↑