SparseTSF: Modeling Long-term Time Series Forecasting with *1k* Parameters

Shengsheng Lin, Weiwei Lin, Wentai Wu, Haojun Chen, Junjie Yang
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:30211-30226, 2024.

Abstract

This paper introduces SparseTSF, a novel, extremely lightweight model for Long-term Time Series Forecasting (LTSF), designed to address the challenges of modeling complex temporal dependencies over extended horizons with minimal computational resources. At the heart of SparseTSF lies the Cross-Period Sparse Forecasting technique, which simplifies the forecasting task by decoupling the periodicity and trend in time series data. This technique involves downsampling the original sequences to focus on cross-period trend prediction, effectively extracting periodic features while minimizing the model’s complexity and parameter count. Based on this technique, the SparseTSF model uses fewer than 1k parameters to achieve competitive or superior performance compared to state-of-the-art models. Furthermore, SparseTSF showcases remarkable generalization capabilities, making it well-suited for scenarios with limited computational resources, small samples, or low-quality data. The code is publicly available at this repository: https://github.com/lss-1138/SparseTSF.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-lin24n, title = {{S}parse{TSF}: Modeling Long-term Time Series Forecasting with *1k* Parameters}, author = {Lin, Shengsheng and Lin, Weiwei and Wu, Wentai and Chen, Haojun and Yang, Junjie}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {30211--30226}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/lin24n/lin24n.pdf}, url = {https://proceedings.mlr.press/v235/lin24n.html}, abstract = {This paper introduces SparseTSF, a novel, extremely lightweight model for Long-term Time Series Forecasting (LTSF), designed to address the challenges of modeling complex temporal dependencies over extended horizons with minimal computational resources. At the heart of SparseTSF lies the Cross-Period Sparse Forecasting technique, which simplifies the forecasting task by decoupling the periodicity and trend in time series data. This technique involves downsampling the original sequences to focus on cross-period trend prediction, effectively extracting periodic features while minimizing the model’s complexity and parameter count. Based on this technique, the SparseTSF model uses fewer than 1k parameters to achieve competitive or superior performance compared to state-of-the-art models. Furthermore, SparseTSF showcases remarkable generalization capabilities, making it well-suited for scenarios with limited computational resources, small samples, or low-quality data. The code is publicly available at this repository: https://github.com/lss-1138/SparseTSF.} }
Endnote
%0 Conference Paper %T SparseTSF: Modeling Long-term Time Series Forecasting with *1k* Parameters %A Shengsheng Lin %A Weiwei Lin %A Wentai Wu %A Haojun Chen %A Junjie Yang %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-lin24n %I PMLR %P 30211--30226 %U https://proceedings.mlr.press/v235/lin24n.html %V 235 %X This paper introduces SparseTSF, a novel, extremely lightweight model for Long-term Time Series Forecasting (LTSF), designed to address the challenges of modeling complex temporal dependencies over extended horizons with minimal computational resources. At the heart of SparseTSF lies the Cross-Period Sparse Forecasting technique, which simplifies the forecasting task by decoupling the periodicity and trend in time series data. This technique involves downsampling the original sequences to focus on cross-period trend prediction, effectively extracting periodic features while minimizing the model’s complexity and parameter count. Based on this technique, the SparseTSF model uses fewer than 1k parameters to achieve competitive or superior performance compared to state-of-the-art models. Furthermore, SparseTSF showcases remarkable generalization capabilities, making it well-suited for scenarios with limited computational resources, small samples, or low-quality data. The code is publicly available at this repository: https://github.com/lss-1138/SparseTSF.
APA
Lin, S., Lin, W., Wu, W., Chen, H. & Yang, J.. (2024). SparseTSF: Modeling Long-term Time Series Forecasting with *1k* Parameters. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:30211-30226 Available from https://proceedings.mlr.press/v235/lin24n.html.

Related Material