系统梳理时间序列的分布外泛化方法，助力模型应对动态环境挑战。
Out-of-Distribution Generalization in Time Series: A Survey
- 从数据分布、表征学习、评估方法三维度构建分析框架
- 归纳多类算法并揭示其在非平稳时序中的适应机制
- 适合关注时序建模鲁棒性的研究者与工业应用开发者
时间序列常面临分布漂移、多样隐含特征和非平稳学习动态，尤其在开放与演化环境中。这些特性给分布外（OOD）泛化带来重大挑战。尽管已有显著进展，但系统性综述仍显不足。为此，本文首次全面回顾时间序列的OOD泛化方法，按数据分布、表征学习和OOD评估三个基础维度组织分析，详述多种主流算法。同时强调关键应用场景，凸显其实际影响。最后，识别持续存在的挑战并提出未来研究方向。所评方法详情可访问 https://tsood-generalization.com。
原文摘要 · Abstract (English)
Time series frequently manifest distribution shifts, diverse latent features, and non-stationary learning dynamics, particularly in open and evolving environments. These characteristics pose significant challenges for out-of-distribution (OOD) generalization. While substantial progress has been made, a systematic synthesis of advancements remains lacking. To address this gap, we present the first comprehensive review of OOD generalization methodologies for time series, organized to delineate the field's evolutionary trajectory and contemporary research landscape. We organize our analysis across three foundational dimensions: data distribution, representation learning, and OOD evaluation. For each dimension, we present several popular algorithms in detail. Furthermore, we highlight key application scenarios, emphasizing their real-world impact. Finally, we identify persistent challenges and propose future research directions. A detailed summary of the methods reviewed for the generalization of OOD in time series can be accessed at https://tsood-generalization.com.
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。