LightGTS: A Lightweight General Time Series Forecasting Model

Yihang Wang, Yuying Qiu, Peng Chen, Yang Shu, Zhongwen Rao, Lujia Pan, Bin Yang, Chenjuan Guo
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:64109-64126, 2025.

Abstract

Existing works on general time series forecasting build foundation models with heavy model parameters through large-scale multi-source pretraining. These models achieve superior generalization ability across various datasets at the cost of significant computational burdens and limitations in resource-constrained scenarios. This paper introduces LightGTS, a lightweight general time series forecasting model designed from the perspective of consistent periodical modeling. To handle diverse scales and intrinsic periods in multi-source pre-training, we introduce Periodical Tokenization, which extracts consistent periodic patterns across different datasets with varying scales. To better utilize the periodicity in the decoding process, we further introduce Periodical Parallel Decoding, which leverage historical tokens to improve forecasting. Based on the two techniques above which fully leverage the inductive bias of periods inherent in time series, LightGTS uses a lightweight model to achieve outstanding performance on general time series forecasting. It achieves state-of-the-art forecasting performance on 9 real-world benchmarks in both zero-shot and full-shot setting with much better efficiency compared with existing time series foundation models

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-wang25ch, title = {{L}ight{GTS}: A Lightweight General Time Series Forecasting Model}, author = {Wang, Yihang and Qiu, Yuying and Chen, Peng and Shu, Yang and Rao, Zhongwen and Pan, Lujia and Yang, Bin and Guo, Chenjuan}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {64109--64126}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/wang25ch/wang25ch.pdf}, url = {https://proceedings.mlr.press/v267/wang25ch.html}, abstract = {Existing works on general time series forecasting build foundation models with heavy model parameters through large-scale multi-source pretraining. These models achieve superior generalization ability across various datasets at the cost of significant computational burdens and limitations in resource-constrained scenarios. This paper introduces LightGTS, a lightweight general time series forecasting model designed from the perspective of consistent periodical modeling. To handle diverse scales and intrinsic periods in multi-source pre-training, we introduce Periodical Tokenization, which extracts consistent periodic patterns across different datasets with varying scales. To better utilize the periodicity in the decoding process, we further introduce Periodical Parallel Decoding, which leverage historical tokens to improve forecasting. Based on the two techniques above which fully leverage the inductive bias of periods inherent in time series, LightGTS uses a lightweight model to achieve outstanding performance on general time series forecasting. It achieves state-of-the-art forecasting performance on 9 real-world benchmarks in both zero-shot and full-shot setting with much better efficiency compared with existing time series foundation models} }
Endnote
%0 Conference Paper %T LightGTS: A Lightweight General Time Series Forecasting Model %A Yihang Wang %A Yuying Qiu %A Peng Chen %A Yang Shu %A Zhongwen Rao %A Lujia Pan %A Bin Yang %A Chenjuan Guo %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-wang25ch %I PMLR %P 64109--64126 %U https://proceedings.mlr.press/v267/wang25ch.html %V 267 %X Existing works on general time series forecasting build foundation models with heavy model parameters through large-scale multi-source pretraining. These models achieve superior generalization ability across various datasets at the cost of significant computational burdens and limitations in resource-constrained scenarios. This paper introduces LightGTS, a lightweight general time series forecasting model designed from the perspective of consistent periodical modeling. To handle diverse scales and intrinsic periods in multi-source pre-training, we introduce Periodical Tokenization, which extracts consistent periodic patterns across different datasets with varying scales. To better utilize the periodicity in the decoding process, we further introduce Periodical Parallel Decoding, which leverage historical tokens to improve forecasting. Based on the two techniques above which fully leverage the inductive bias of periods inherent in time series, LightGTS uses a lightweight model to achieve outstanding performance on general time series forecasting. It achieves state-of-the-art forecasting performance on 9 real-world benchmarks in both zero-shot and full-shot setting with much better efficiency compared with existing time series foundation models
APA
Wang, Y., Qiu, Y., Chen, P., Shu, Y., Rao, Z., Pan, L., Yang, B. & Guo, C.. (2025). LightGTS: A Lightweight General Time Series Forecasting Model. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:64109-64126 Available from https://proceedings.mlr.press/v267/wang25ch.html.

Related Material