Abstract:Time series, characterized by a sequence of data points organized in a discrete-time order, are ubiquitous in real-world scenarios. Unlike other data modalities, time series present unique challenges in learning and modeling due to their intricate and dynamic nature, including the entanglement of nonlinear patterns and time-variant trends. Recent years have witnessed remarkable breakthroughs in time series analysis, with techniques shifting from traditional statistical methods to contemporary deep learning models. In this paper, we delve into the design of deep time series models across various analysis tasks and review the existing literature from two perspectives: basic modules and model architectures. Further, we develop and release Time Series Library (TSLib) as a fair benchmark of deep time series models for diverse analysis tasks. TSLib implements 41 prominent models, including both small- and large-scale time series models, covers 30 datasets from different domains, and supports 5 prevalent analysis tasks. Based on TSLib, we evaluate 16 popular deep time series models and 6 advanced time series foundation models. Empirical findings indicate that models with specific structures are apt only at distinct analytical tasks, providing insights for research and adoption of deep time series models. Code and datasets are available at this https URL.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2407.13278 [cs.LG] |
| (or arXiv:2407.13278v3 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2407.13278 arXiv-issued DOI via DataCite |
From: Yuxuan Wang [view email]
[v1]
Thu, 18 Jul 2024 08:31:55 UTC (11,614 KB)
[v2]
Sat, 27 Sep 2025 03:57:17 UTC (11,764 KB)
[v3]
Mon, 4 May 2026 08:07:42 UTC (11,951 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。