We propose Feature-aligned N-BEATS as a domain-generalized time series forecasting model. It is a nontrivial extension of N-BEATS with doubly residual stacking principle (Oreshkin et al.[42]) into a representation learning framework. In particular, it revolves around marginal feature probability measures induced by the intricate composition of residual and feature extracting operators of N-BEATS in each stack and aligns them stack-wisely via an approximate of an optimal transport distance referred to as the Sinkhorn divergence. The training loss consists of an empirical risk minimization from multiple source domains, i.e., forecasting loss, and an alignment loss calculated with the Sinkhorn divergence, which allows the model to learn invariant features stack-wisely across multiple source data sequences while retaining N-BEATS's interpretable design and forecasting power. Comprehensive experimental evaluations with ablation studies are provided and the corresponding results demonstrate the proposed model's forecasting and generalization capabilities.

翻译：我们提出特征对齐的N-BEATS（Feature-aligned N-BEATS）作为领域泛化时间序列预测模型。该模型是将具有双残差堆叠原则的N-BEATS（Oreshkin等人[42]）扩展到表示学习框架的重要扩展。具体而言，该模型围绕由N-BEATS在每个堆栈中残差与特征提取算子的复杂组合所诱导的边缘特征概率测度展开，并通过最优传输距离的近似——即Sinkhorn散度——以堆栈方式对其对齐。训练损失由来自多个源域的经验风险最小化（即预测损失）和通过Sinkhorn散度计算的对齐损失组成，这使得模型能够在跨多个源数据序列的堆栈层面学习不变特征，同时保留N-BEATS的可解释性设计与预测能力。我们提供了包含消融实验的全面实验评估，相应结果证明了所提模型的预测与泛化能力。