解决不规则多变量时间序列的时空建模难题，实现精准预测。
Bridging Time and Frequency: A Joint Modeling Framework for Irregular Multivariate Time Series Forecasting
- 联合时频域建模，用可学习的非均匀傅里叶变换提取频谱特征。
- 通过查询驱动的局部块混合缓解采样不均导致的信息密度失衡。
- 首次在不规则数据上实现显式季节性外推，适合医疗、金融等场景。
不规则多变量时间序列预测（IMTSF）因采样不均与异步性而极具挑战，传统模型依赖等距假设，破坏了局部时序建模能力，且经典频域方法无法捕捉全局周期结构。为此，我们提出TFMixer——一种联合时频建模框架。其核心包括：全局频率模块利用可学习的非均匀离散傅里叶变换（NUDFT），直接从不规则时间戳中提取频谱表示；局部时间模块引入查询驱动的块混合机制，自适应聚合有效时间片段，缓解信息密度不平衡问题；最终融合时频表示生成预测，并借助逆NUDFT实现显式季节性外推。在多个真实数据集上的实验表明，TFMixer达到当前最优性能。
原文摘要 · Abstract (English)
Irregular multivariate time series forecasting (IMTSF) is challenging due to non-uniform sampling and variable asynchronicity. These irregularities violate the equidistant assumptions of standard models, hindering local temporal modeling and rendering classical frequency-domain methods ineffective for capturing global periodic structures. To address this challenge, we propose TFMixer, a joint time-frequency modeling framework for IMTS forecasting. Specifically, TFMixer incorporates a Global Frequency Module that employs a learnable Non-Uniform Discrete Fourier Transform (NUDFT) to directly extract spectral representations from irregular timestamps. In parallel, the Local Time Module introduces a query-based patch mixing mechanism to adaptively aggregate informative temporal patches and alleviate information density imbalance. Finally, TFMixer fuses the time-domain and frequency-domain representations to generate forecasts and further leverages inverse NUDFT for explicit seasonal extrapolation. Extensive experiments on real-world datasets demonstrate the state--of-the-art performance of TFMixer.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。