鲁棒多元时间序列预测：应对序列内与序列间转移偏移
Robust Multivariate Time Series Forecasting against Intra- and Inter-Series Transitional Shift
AI总结：
针对多元时间序列预测中的分布偏移问题，提出联合概率图模型JointPGM，同时捕捉序列内与序列间相关性并建模时变转移分布，在六个非平稳数据集上取得最优性能。
摘要：
现实世界多元时间序列（MTS）数据的非平稳性给预测模型带来了时间序列时变分布的严峻挑战，即所谓的分布偏移。现有关于分布偏移的研究大多采用自适应归一化技术来缓解时间均值和协方差偏移，或采用时变建模来捕捉时间偏移。尽管这些基于归一化的方法提高了模型泛化能力，但它们通常假设输出与输入之间的转移关系是时间不变的，且忽略了特定的序列内/序列间相关性，而时变模型则忽视了分布偏移的内在原因。这限制了模型在应对MTS预测中分布偏移时的表达能力和可解释性。为缓解这一困境，我们提出一个统一的概率图模型，联合捕捉序列内/序列间相关性并建模时变转移分布，并实例化一个名为JointPGM的神经框架用于非平稳MTS预测。具体而言，JointPGM首先采用多个傅里叶基函数学习动态时间因子，并设计两个不同的学习器：序列内学习器和序列间学习器。序列内学习器通过利用时间门有效捕捉时间动态，而序列间学习器通过多跳传播显式建模空间动态，并结合Gumbel-softmax采样。这两种序列动态随后融合到一个潜变量中，该潜变量被反向用于推断时间因子、生成最终预测并执行重构。我们在六个高度非平稳的MTS数据集上通过大量实验验证了JointPGM的有效性和效率，实现了MTS预测的最先进预测性能。
英文摘要：
The non-stationary nature of real-world Multivariate Time Series (MTS) data presents forecasting models with a formidable challenge of the time-variant distribution of time series, referred to as distribution shift. Existing studies on the distribution shift mostly adhere to adaptive normalization techniques for alleviating temporal mean and covariance shifts or time-variant modeling for capturing temporal shifts. Despite improving model generalization, these normalization-based methods often assume a time-invariant transition between outputs and inputs but disregard specific intra-/inter-series correlations, while time-variant models overlook the intrinsic causes of the distribution shift. This limits model expressiveness and interpretability of tackling the distribution shift for MTS forecasting. To mitigate such a dilemma, we present a unified Probabilistic Graphical Model to Jointly capturing intra-/inter-series correlations and modeling the time-variant transitional distribution, and instantiate a neural framework called JointPGM for non-stationary MTS forecasting. Specifically, JointPGM first employs multiple Fourier basis functions to learn dynamic time factors and designs two distinct learners: intra-series and inter-series learners. The intra-series learner effectively captures temporal dynamics by utilizing temporal gates, while the inter-series learner explicitly models spatial dynamics through multi-hop propagation, incorporating Gumbel-softmax sampling. These two types of series dynamics are subsequently fused into a latent variable, which is inversely employed to infer time factors, generate final prediction, and perform reconstruction. We validate the effectiveness and efficiency of JointPGM through extensive experiments on six highly non-stationary MTS datasets, achieving state-of-the-art forecasting performance of MTS forecasting.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
