用去噪图网络提升长期多变量时间序列预测精度
From Noise to Laws: Regularized Time-Series Forecasting via Denoised Dynamic Graphs
- 通过扩散模型预处理信号并构建动态相关性图
- 在6个基准上达到最优，均方误差和平均绝对误差显著降低
- 融合物理规律约束，适合对稳定性要求高的场景
长期多变量时间序列预测面临三大挑战：（i）消除异构信号噪声，（ii）追踪随时间变化的跨序列依赖关系，（iii）在长时程推演中保持稳定与物理合理性。我们提出PRISM，将基于得分的扩散预处理器与动态相关性阈值图编码器结合，并使用通用物理惩罚项正则化预测头。我们在温和条件下证明了模型诱导的时序动态收缩性，并推导出图模块的Lipschitz边界，解释其鲁棒性。在六个标准基准上，PRISM实现一致的最先进性能，均方误差（MSE）和平均绝对误差（MAE）均有显著提升。
原文摘要 · Abstract (English)
Long-horizon multivariate time-series forecasting is challenging because realistic predictions must (i) denoise heterogeneous signals, (ii) track time-varying cross-series dependencies, and (iii) remain stable and physically plausible over long rollout horizons. We present PRISM, which couples a score-based diffusion preconditioner with a dynamic, correlation-thresholded graph encoder and a forecast head regularized by generic physics penalties. We prove contraction of the induced horizon dynamics under mild conditions and derive Lipschitz bounds for graph blocks, explaining the model's robustness. On six standard benchmarks , PRISM achieves consistent SOTA with strong MSE and MAE gains.
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。