Deep Time-Series Forecasting in 10 Years: A Survey
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026 · 1-20
DOI: 10.1109/tpami.2026.3742172 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026. Verfasst von Hao Wang und 14 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref).
Abstract (Originalsprache)
Autocorrelation is a common property of time-series, where each observation is dependent on its predecessors. In deep time-series forecasting, it raises two central challenges: ❶ designing backbone architectures to model autocorrelation in history sequences, and ❷ devising loss functions to model autocorrelation in label sequences. Recent studies have made strides in tackling these challenges, but a systematic survey examining both aspects remains lacking. To bridge this gap, this paper reviews deep time-series forecasting from an autocorrelation modeling perspective, offering two contributions beyond existing surveys. First, it introduces a taxonomy that jointly covers both backbone architectures and loss functions, whereas prior surveys provide limited coverage of the latter. Second, it analyzes the motivations and insights underlying the surveyed literature from a unified autocorrelation modeling perspective, providing a holistic overview of the field's evolution.
Zitieren
APA
Wang, H., Pan, L., Wen, Q., Yu, J., Chen, Z., Zheng, C., Li, X., Chu, Z., Xu, C., Gong, M., Li, H., Lu, Y., Lin, Z., Torr, P., & Liu, Y. (2026). Deep Time-Series Forecasting in 10 Years: A Survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1-20. https://doi.org/10.1109/tpami.2026.3742172
Vancouver
Wang H, Pan L, Wen Q, Yu J, Chen Z, Zheng C, et al. Deep Time-Series Forecasting in 10 Years: A Survey. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026:1-20. doi:10.1109/tpami.2026.3742172
BibTeX
@article{Wang2026,
author = {Wang, Hao and Pan, Licheng and Wen, Qingsong and Yu, Jialin and Chen, Zhichao and Zheng, Chunyuan and Li, Xiaoxi and Chu, Zhixuan and Xu, Chao and Gong, Mingming and Li, Haoxuan and Lu, Yuan and Lin, Zhouchen and Torr, Philip and Liu, Yan},
title = {Deep Time-Series Forecasting in 10 Years: A Survey},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2026},
pages = {1--20},
doi = {10.1109/tpami.2026.3742172}
}
EUVIMED