A Unified Frequency Domain Decomposition Framework for Interpretable and Robust Time Series Forecasting
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908587641536512 |
|---|---|
| author | He, Cheng Liang, Xijie Zheng, Zengrong Lee, Patrick P. C. Huang, Xu Li, Zhaoyi Xie, Hong Lian, Defu Chen, Enhong |
| author_facet | He, Cheng Liang, Xijie Zheng, Zengrong Lee, Patrick P. C. Huang, Xu Li, Zhaoyi Xie, Hong Lian, Defu Chen, Enhong |
| contents | Current approaches for time series forecasting, whether in the time or frequency domain, predominantly use deep learning models based on linear layers or transformers. They often encode time series data in a black-box manner and rely on trial-and-error optimization solely based on forecasting performance, leading to limited interpretability and theoretical understanding. Furthermore, the dynamics in data distribution over time and frequency domains pose a critical challenge to accurate forecasting. We propose FIRE, a unified frequency domain decomposition framework that provides a mathematical abstraction for diverse types of time series, so as to achieve interpretable and robust time series forecasting. FIRE introduces several key innovations: (i) independent modeling of amplitude and phase components, (ii) adaptive learning of weights of frequency basis components, (iii) a targeted loss function, and (iv) a novel training paradigm for sparse data. Extensive experiments demonstrate that FIRE consistently outperforms state-of-the-art models on long-term forecasting benchmarks, achieving superior predictive performance and significantly enhancing interpretability of time series |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_10145 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Unified Frequency Domain Decomposition Framework for Interpretable and Robust Time Series Forecasting He, Cheng Liang, Xijie Zheng, Zengrong Lee, Patrick P. C. Huang, Xu Li, Zhaoyi Xie, Hong Lian, Defu Chen, Enhong Machine Learning Artificial Intelligence Current approaches for time series forecasting, whether in the time or frequency domain, predominantly use deep learning models based on linear layers or transformers. They often encode time series data in a black-box manner and rely on trial-and-error optimization solely based on forecasting performance, leading to limited interpretability and theoretical understanding. Furthermore, the dynamics in data distribution over time and frequency domains pose a critical challenge to accurate forecasting. We propose FIRE, a unified frequency domain decomposition framework that provides a mathematical abstraction for diverse types of time series, so as to achieve interpretable and robust time series forecasting. FIRE introduces several key innovations: (i) independent modeling of amplitude and phase components, (ii) adaptive learning of weights of frequency basis components, (iii) a targeted loss function, and (iv) a novel training paradigm for sparse data. Extensive experiments demonstrate that FIRE consistently outperforms state-of-the-art models on long-term forecasting benchmarks, achieving superior predictive performance and significantly enhancing interpretability of time series |
| title | A Unified Frequency Domain Decomposition Framework for Interpretable and Robust Time Series Forecasting |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2510.10145 |