Time series forecasting plays a fundamental role across diverse domains including energy systems, transportation, healthcare, etc. Despite significant advancements in forecasting models, their practical application often encounters challenges due to distribution shifts, where the statistical properties of testing data deviate from those of training data. Such shifts can severely degrade model performance, necessitating frequent retraining with the latest data to maintain performance. To address this limitation, we introduce FreqMoE, a framework designed for out-of-distribution (OOD) scenarios. Our proposed method applies random masking as a regularization strategy and utilizes a Mixture of Experts (MoE) network to encourage robust frequency-domain representations. Each expert focuses on modeling specific frequency characteristics and the MoE dynamically selects experts based on spectrum embedding, capturing frequency-domain patterns by modeling sequences in the frequency domain. Experimental results on diverse real-world datasets demonstrate that FreqMoE achieves competitive or leading performance compared to existing approaches in both prediction accuracy and robustness under OOD scenarios, demonstrating improved robustness under naturalistic temporal distribution shifts.
Shen et al. (Wed,) studied this question.