GARDiff：面向概率多变量时间序列预测的图对齐残差扩散
GARDiff: Graph-Aligned Residual Diffusion for Probabilistic Multivariate Time-Series Forecasting
- Shandong University（山东大学）
- Macquarie University（麦考瑞大学）
- China University of Petroleum (East China)（中国石油大学（华东））
- University of Technology Sydney（悉尼科技大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
GARDiff提出图对齐残差扩散框架，通过不确定性感知结构细化和时间步感知边稀疏化，解决解耦扩散预测中确定性图与残差结构的错位问题，提升概率预测性能。
AI中文摘要：
扩散模型最近通过建模复杂的条件分布，在概率多变量时间序列预测中展现出强大的潜力。最近的解耦扩散框架进一步将预测分为确定性预测和随机残差生成，使得从确定性表示中推导依赖图并利用其指导残差扩散变得自然。然而，我们表明这种直接的结构转移是不可靠的。尽管从确定性推导出的图编码了有用的全局依赖先验，但它们与残差依赖结构存在显著的边级错位，在残差生成过程中引入了不准确或冗余的条件。这揭示了解耦扩散预测中一个先前被忽视的确定性到残差的结构对齐问题。为解决此问题，我们提出了GARDiff，一种用于概率多变量时间序列预测的图对齐残差扩散框架。GARDiff不是将确定性推导的图视为固定的扩散条件，而是逐步使其适应残差生成。具体来说，GARDiff估计残差不确定性以区分高不确定性和低不确定性区域，实现不确定性感知的结构细化，并在反向扩散过程中执行时间步感知的边稀疏化，使图条件从广泛的依赖聚合演变为局部的残差细化。在六个真实世界基准上的大量实验表明，GARDiff在概率预测性能和不确定性校准方面持续优于强基线。
英文摘要：
Diffusion models have recently shown strong potential for probabilistic multivariate time-series forecasting by modeling complex conditional distributions. Recent decoupled diffusion frameworks further separate forecasting into deterministic prediction and stochastic residual generation, making it natural to derive dependency graphs from deterministic representations and use them to guide residual diffusion. However, we show that this direct structural transfer is unreliable. Although deterministic-derived graphs encode useful global dependency priors, they exhibit substantial edge-level misalignment with residual dependency structures, introducing inaccurate or redundant conditions during residual generation. This reveals a previously overlooked deterministic-to-residual structural alignment problem in decoupled diffusion forecasting. To address this problem, we propose GARDiff, a Graph-Aligned Residual Diffusion framework for probabilistic multivariate time-series forecasting. Instead of treating deterministic-derived graphs as fixed diffusion conditions, GARDiff progressively adapts them to residual generation. Specifically, GARDiff estimates residual uncertainty to distinguish high- and low-uncertainty regions, enabling uncertainty-aware structural refinement, and further performs timestep-aware edge sparsification during reverse diffusion to evolve graph conditions from broad dependency aggregation to localized residual refinement. Extensive experiments on six real-world benchmarks demonstrate that GARDiff consistently improves probabilistic forecasting performance and uncertainty calibration over strong baselines.
