arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.17436cs.LGcs.AI
收藏

TimeAPN: 用于时间序列预测的自适应幅度-相位非平稳归一化

TimeAPN: Adaptive Amplitude-Phase Non-Stationarity Normalization for Time Series Forecasting

School of Mathematics, Harbin Institute of Technology(哈尔滨工业大学数学学院);School of Computer Science and Engineering, Nanjing University of Science and Technology(南京理工大学计算机科学与工程学院);Lee Kong Chian School of Medicine, Nanyang Technological University(南洋理工大学李科钦医学院);School of Computer Science, Wuhan University(武汉大学计算机学院);College of Computing and Data Science, Nanyang Technological University(南洋理工大学计算与数据科学学院)

Yue Hu, Jialiang Tang, Siwei Yu, Baosheng Yu, Jing Zhang, Dacheng Tao

AI总结:

本文提出TimeAPN框架,通过时间与频率域联合建模和预测非平稳因素,结合自适应归一化机制提升长周期时间序列预测精度。

摘要:

非平稳性是多变量长周期时间序列预测中的根本挑战,通常表现为幅度和相位的快速变化。这些变化导致严重的分布偏移,从而降低预测性能。现有基于归一化的办法主要依赖一阶和二阶统计量,隐含假设分布演变平滑,忽略了细粒度的时间动态。为了解决这些限制,我们提出了TimeAPN,一种自适应幅度-相位非平稳归一化框架,该框架从时间和频率域显式建模和预测非平稳因素。具体而言,TimeAPN首先在时间和频率域联合建模均值序列,然后预测其未来演变。同时,相位信息在频率域中提取,相位差异在预测和真实未来序列之间被显式建模以捕捉时间偏移。此外,TimeAPN将幅度信息纳入自适应归一化机制,使模型能够有效应对信号能量的突然波动。预测的非平稳因素随后通过协作去归一化过程与基础预测输出整合,以重建最终的非平稳时间序列。所提框架是模型无关的,可无缝集成各种预测基础架构。在七个真实世界多变量数据集上的广泛实验表明,TimeAPN在多个预测时间跨度上均提升了长期预测精度,并优于最先进的可逆归一化方法。

英文摘要:

Non-stationarity is a fundamental challenge in multivariate long-term time series forecasting, often manifested as rapid changes in amplitude and phase. These variations lead to severe distribution shifts and consequently degrade predictive performance. Existing normalization-based methods primarily rely on first- and second-order statistics, implicitly assuming that distributions evolve smoothly and overlooking fine-grained temporal dynamics. To address these limitations, we propose TimeAPN, an Adaptive Amplitude-Phase Non-Stationarity Normalization framework that explicitly models and predicts non-stationary factors from both the time and frequency domains. Specifically, TimeAPN first models the mean sequence jointly in the time and frequency domains, and then forecasts its evolution over future horizons. Meanwhile, phase information is extracted in the frequency domain, and the phase discrepancy between the predicted and ground-truth future sequences is explicitly modeled to capture temporal misalignment. Furthermore, TimeAPN incorporates amplitude information into an adaptive normalization mechanism, enabling the model to effectively account for abrupt fluctuations in signal energy. The predicted non-stationary factors are subsequently integrated with the backbone forecasting outputs through a collaborative de-normalization process to reconstruct the final non-stationary time series. The proposed framework is model-agnostic and can be seamlessly integrated with various forecasting backbones. Extensive experiments on seven real-world multivariate datasets demonstrate that TimeAPN consistently improves long-term forecasting accuracy across multiple prediction horizons and outperforms state-of-the-art reversible normalization methods.

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。

↑