CFPT: Empowering Time Series Forecasting through Cross-Frequency Interaction and Periodic-Aware Timestamp Modeling

Feifei Kou, Jiahao Wang, Lei Shi, Yuhan Yao, Yawen Li, Suguo Zhu, Zhongbao Zhang, Junping Du
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:31634-31647, 2025.

Abstract

Long-term time series forecasting has been widely studied, yet two aspects remain insufficiently explored: the interaction learning between different frequency components and the exploitation of periodic characteristics inherent in timestamps. To address the above issues, we propose CFPT, a novel method that empowering time series forecasting through Cross-Frequency Interaction (CFI) and Periodic-Aware Timestamp Modeling (PTM). To learn cross-frequency interactions, we design the CFI branch to process signals in frequency domain and captures their interactions through a feature fusion mechanism. Furthermore, to enhance prediction performance by leveraging timestamp periodicity, we develop the PTM branch which transforms timestamp sequences into 2D periodic tensors and utilizes 2D convolution to capture both intra-period dependencies and inter-period correlations of time series based on timestamp patterns. Extensive experiments on multiple real-world benchmarks demonstrate that CFPT achieves state-of-the-art performance in long-term forecasting tasks. The code is publicly available at this repository: https://github.com/BUPT-SN/CFPT.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-kou25b, title = {{CFPT}: Empowering Time Series Forecasting through Cross-Frequency Interaction and Periodic-Aware Timestamp Modeling}, author = {Kou, Feifei and Wang, Jiahao and Shi, Lei and Yao, Yuhan and Li, Yawen and Zhu, Suguo and Zhang, Zhongbao and Du, Junping}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {31634--31647}, 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/kou25b/kou25b.pdf}, url = {https://proceedings.mlr.press/v267/kou25b.html}, abstract = {Long-term time series forecasting has been widely studied, yet two aspects remain insufficiently explored: the interaction learning between different frequency components and the exploitation of periodic characteristics inherent in timestamps. To address the above issues, we propose CFPT, a novel method that empowering time series forecasting through Cross-Frequency Interaction (CFI) and Periodic-Aware Timestamp Modeling (PTM). To learn cross-frequency interactions, we design the CFI branch to process signals in frequency domain and captures their interactions through a feature fusion mechanism. Furthermore, to enhance prediction performance by leveraging timestamp periodicity, we develop the PTM branch which transforms timestamp sequences into 2D periodic tensors and utilizes 2D convolution to capture both intra-period dependencies and inter-period correlations of time series based on timestamp patterns. Extensive experiments on multiple real-world benchmarks demonstrate that CFPT achieves state-of-the-art performance in long-term forecasting tasks. The code is publicly available at this repository: https://github.com/BUPT-SN/CFPT.} }
Endnote
%0 Conference Paper %T CFPT: Empowering Time Series Forecasting through Cross-Frequency Interaction and Periodic-Aware Timestamp Modeling %A Feifei Kou %A Jiahao Wang %A Lei Shi %A Yuhan Yao %A Yawen Li %A Suguo Zhu %A Zhongbao Zhang %A Junping Du %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-kou25b %I PMLR %P 31634--31647 %U https://proceedings.mlr.press/v267/kou25b.html %V 267 %X Long-term time series forecasting has been widely studied, yet two aspects remain insufficiently explored: the interaction learning between different frequency components and the exploitation of periodic characteristics inherent in timestamps. To address the above issues, we propose CFPT, a novel method that empowering time series forecasting through Cross-Frequency Interaction (CFI) and Periodic-Aware Timestamp Modeling (PTM). To learn cross-frequency interactions, we design the CFI branch to process signals in frequency domain and captures their interactions through a feature fusion mechanism. Furthermore, to enhance prediction performance by leveraging timestamp periodicity, we develop the PTM branch which transforms timestamp sequences into 2D periodic tensors and utilizes 2D convolution to capture both intra-period dependencies and inter-period correlations of time series based on timestamp patterns. Extensive experiments on multiple real-world benchmarks demonstrate that CFPT achieves state-of-the-art performance in long-term forecasting tasks. The code is publicly available at this repository: https://github.com/BUPT-SN/CFPT.
APA
Kou, F., Wang, J., Shi, L., Yao, Y., Li, Y., Zhu, S., Zhang, Z. & Du, J.. (2025). CFPT: Empowering Time Series Forecasting through Cross-Frequency Interaction and Periodic-Aware Timestamp Modeling. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:31634-31647 Available from https://proceedings.mlr.press/v267/kou25b.html.

Related Material