将时间序列分解为趋势与季节分量，分别用线性与扩散模型建模，提升预测精度。
Conditional Denoising Meets Polynomial Modeling: A Flexible Decoupled Framework for Time Series Forecasting
- 将时间序列拆解为趋势和季节分量，分开展示建模。
- 在6个基准数据集上优于现有方法，显著提升预测准确率。
- 适合需要高精度预测的金融、气象等场景。
时间序列预测模型在多个领域决策中日益重要。然而，多数现有方法将时间模式耦合建模，忽略了其内部成分的差异。波动性季节分量与平滑趋势分量具有不同特征。本文提出条件去噪多项式建模（CDPM）框架，将概率扩散模型与确定性线性模型端到端联合训练。不同于联合建模，CDPM将时间序列分解为趋势与季节分量，并分别建模。针对波动性季节分量，基于历史窗口统计特性采用概率扩散模型；针对平滑趋势分量，设计模块增强线性模型的历史依赖建模能力，以保留底层趋势并减少噪声干扰。在六个基准数据集上的大量实验验证了该框架的有效性，展示了概率与确定性模型结合的潜力。代码已公开于 https://github.com/zjt-gpu/CDPM。
原文摘要 · Abstract (English)
Time series forecasting models are becoming increasingly prevalent due to their critical role in decision-making across various domains. However, most existing approaches represent the coupled temporal patterns, often neglecting the distinction between their specific components. In particular, fluctuating patterns and smooth trends within time series exhibit distinct characteristics. In this work, to model complicated temporal patterns, we propose a Conditional Denoising Polynomial Modeling (CDPM) framework, where probabilistic diffusion models and deterministic linear models are trained end-to-end. Instead of modeling the coupled time series, CDPM decomposes it into trend and seasonal components for modeling them separately. To capture the fluctuating seasonal component, we employ a probabilistic diffusion model based on statistical properties from the historical window. For the smooth trend component, a module is proposed to enhance linear models by incorporating historical dependencies, thereby preserving underlying trends and mitigating noise distortion. Extensive experiments conducted on six benchmarks demonstrate the effectiveness of our framework, highlighting the potential of combining probabilistic and deterministic models. Our code is available at https://github.com/zjt-gpu/CDPM.
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。