动态引导扩散模型提升多变量时间序列预测的鲁棒性
DynG-Diff: A State-Aware Dynamic Guidance Diffusion Framework for Probabilistic Time Series Forecasting
- 分两阶段训练，用无条件扩散模型建模多变量联合分布
- 实时评估变量可靠性，动态生成引导权重矩阵
- 数学上将权重视为观测精度，增强高置信度变量的引导
概率性多变量时间序列（MTS）预测对建模复杂动态系统至关重要。现有基于扩散的方法依赖特定任务的条件范式，灵活性差，难以应对变量间显著不同的噪声水平和演化模式（即“信息异质性”）。为此，我们提出 DynG-Diff：一种面向概率性多变量时间序列预测的变量敏感动态引导扩散框架。首先，采用两阶段分离训练策略，使用无条件扩散骨干网络建模多变量时间序列的联合分布；其次，引入轻量级状态感知策略网络，从实时噪声状态和一步去噪估计中自适应推断变量可靠性，输出动态引导强度矩阵；最后，将该动态权重在数学上形式化为观测分布的局部精度，从而在推理时对高置信度变量进行精确引导，同时过滤异常噪声干扰。在真实世界基准上的大量实验表明，其概率预测性能优于当前主流条件扩散模型，并在严重观测污染下展现出更强鲁棒性。代码已开源：https://github.com/TT-20011031/DynG-Diff。
原文摘要 · Abstract (English)
Probabilistic multivariate time series (MTS) forecasting is crucial for modeling complex dynamical systems. However, existing diffusion-based methods rely on task-specific conditional paradigms that lack flexibility and struggle with inherent "information heterogeneity"--the significantly varying noise levels and evolutionary patterns across variables. To address this, we propose DynG-Diff, a variable-sensitive dynamic guidance diffusion framework for probabilistic multivariate time-series forecasting: (1) DynG-Diff adopts a two-stage separated training strategy and uses an unconditional diffusion backbone to model the joint distribution of multivariate time series. (2) DynG-Diff introduces a lightweight state-aware policy network that adaptively infers variable reliability from real-time noisy states and one-step denoising estimates, outputting a dynamic guidance strength matrix. (3) DynG-Diff mathematically formulates this dynamic weight as the local precision of the observation distribution, enabling precise guidance for high-confidence variables during inference while filtering out interference from anomalous noise. Extensive experiments on real-world benchmarks demonstrate competitive probabilistic forecasting performance against state-of-the-art conditional diffusion models and improved robustness under severe observation corruption.The implementation code is available at: https://github.com/TT-20011031/DynG-Diff
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。