用多尺度自回归生成时间序列，更省参数还更准
TimeMar: Multi-Scale Autoregressive Modeling for Unconditional Time Series Generation
- 多尺度离散化编码，从粗到细逐步生成
- 用双路VQ-VAE分离趋势与周期成分，提升表示质量
- 适合需要长序列生成且资源有限的场景
生成模型为时间序列分析中的数据稀缺和隐私问题提供了可行方案。然而，时间序列固有的多尺度时序模式与异构结构仍未得到充分建模。本文提出一种结构解耦的多尺度生成框架：在多个时间粒度上将序列编码为离散标记，并采用从粗到细的自回归生成方式，保留层次依赖关系。为应对结构异构性，引入双路径VQ-VAE，分离趋势与季节成分，实现语义一致的潜在表征。此外，提出基于引导的重构策略，以粗粒度季节信号作为先验，指导细粒度季节模式的重建。在六个数据集上的实验表明，该方法生成的时间序列质量优于现有方法，且参数量显著减少，在生成高质量长序列方面表现优异。代码已开源。
原文摘要 · Abstract (English)
Generative modeling offers a promising solution to data scarcity and privacy challenges in time series analysis. However, the structural complexity of time series, characterized by multi-scale temporal patterns and heterogeneous components, remains insufficiently addressed. In this work, we propose a structure-disentangled multiscale generation framework for time series. Our approach encodes sequences into discrete tokens at multiple temporal resolutions and performs autoregressive generation in a coarse-to-fine manner, thereby preserving hierarchical dependencies. To tackle structural heterogeneity, we introduce a dual-path VQ-VAE that disentangles trend and seasonal components, enabling the learning of semantically consistent latent representations. Additionally, we present a guidance-based reconstruction strategy, where coarse seasonal signals are utilized as priors to guide the reconstruction of fine-grained seasonal patterns. Experiments on six datasets show that our approach produces higher-quality time series than existing methods. Notably, our model achieves strong performance with a significantly reduced parameter count and exhibits superior capability in generating high-quality long-term sequences. Our implementation is available at https://anonymous.4open.science/r/TimeMAR-BC5B.
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。