Out-of-Distribution Generalization in Time Series: A Survey

• URL: http://arxiv.org/abs/2503.13868v2
• Date: Mon, 07 Apr 2025 03:45:27 GMT
• Title: Out-of-Distribution Generalization in Time Series: A Survey
• Authors: Xin Wu, Fei Teng, Xingwang Li, Ji Zhang, Tianrui Li, Qiang Duan,
• Abstract summary: Time series frequently manifest distribution shifts, diverse latent features, and non-stationary learning dynamics.<n>These characteristics pose significant challenges for out-of-distribution (OOD) generalization.<n>We present the first comprehensive review of OOD generalization methodologies for time series.
• Score: 19.968769520282123
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Deep Learning for Time Series Forecasting: A Survey [12.748035569833451]
  We study the previous works and summarize the general paradigms of Deep Time Series Forecasting (DTSF) in terms of model architectures. We take an innovative approach by focusing on the composition of time series and systematically explain important feature extraction methods.
  arXiv  Detail & Related papers  (2025-03-13T09:32:01Z)
• General Time-series Model for Universal Knowledge Representation of Multivariate Time-Series data [61.163542597764796]
  We show that time series with different time granularities (or corresponding frequency resolutions) exhibit distinct joint distributions in the frequency domain.<n>A novel Fourier knowledge attention mechanism is proposed to enable learning time-aware representations from both the temporal and frequency domains.<n>An autoregressive blank infilling pre-training framework is incorporated to time series analysis for the first time, leading to a generative tasks agnostic pre-training strategy.
  arXiv  Detail & Related papers  (2025-02-05T15:20:04Z)
• Foundation Models for Time Series Analysis: A Tutorial and Survey [70.43311272903334]
  Foundation Models (FMs) have fundamentally reshaped the paradigm of model design for time series analysis. This survey aims to furnish a comprehensive and up-to-date overview of FMs for time series analysis.
  arXiv  Detail & Related papers  (2024-03-21T10:08:37Z)
• Universal Time-Series Representation Learning: A Survey [14.340399848964662]
  Time-series data exists in every corner of real-world systems and services. Deep learning has demonstrated remarkable performance in extracting hidden patterns and features from time-series data.
  arXiv  Detail & Related papers  (2024-01-08T08:00:04Z)
• Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlook [95.32949323258251]
  Temporal data, notably time series andtemporal-temporal data, are prevalent in real-world applications. Recent advances in large language and other foundational models have spurred increased use in time series andtemporal data mining.
  arXiv  Detail & Related papers  (2023-10-16T09:06:00Z)
• DIVERSIFY: A General Framework for Time Series Out-of-distribution Detection and Generalization [58.704753031608625]
  Time series is one of the most challenging modalities in machine learning research. OOD detection and generalization on time series tend to suffer due to its non-stationary property. We propose DIVERSIFY, a framework for OOD detection and generalization on dynamic distributions of time series.
  arXiv  Detail & Related papers  (2023-08-04T12:27:11Z)
• WOODS: Benchmarks for Out-of-Distribution Generalization in Time Series [9.181035389003759]
  We present WOODS: eight challenging open-source time series benchmarks covering a diverse range of data modalities. We revise the existing OOD generalization algorithms for time series tasks and evaluate them using our systematic framework. Our experiments show a large room for improvement for empirical risk minimization and OOD generalization algorithms on our datasets.
  arXiv  Detail & Related papers  (2022-03-18T14:12:54Z)
• Time Series Analysis via Network Science: Concepts and Algorithms [62.997667081978825]
  This review provides a comprehensive overview of existing mapping methods for transforming time series into networks. We describe the main conceptual approaches, provide authoritative references and give insight into their advantages and limitations in a unified notation and language. Although still very recent, this research area has much potential and with this survey we intend to pave the way for future research on the topic.
  arXiv  Detail & Related papers  (2021-10-11T13:33:18Z)
• Towards Out-Of-Distribution Generalization: A Survey [46.329995334444156]
  Out-of-Distribution generalization is an emerging topic of machine learning research. This paper represents the first comprehensive, systematic review of OOD generalization.
  arXiv  Detail & Related papers  (2021-08-31T05:28:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.