Efficient Time Series Forecasting via Hyper-Complex Models and Frequency Aggregation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915175716618240 |
|---|---|
| author | Yakir, Eyal Tsur, Dor Permuter, Haim |
| author_facet | Yakir, Eyal Tsur, Dor Permuter, Haim |
| contents | Time series forecasting is a long-standing problem in statistics and machine learning. One of the key challenges is processing sequences with long-range dependencies. To that end, a recent line of work applied the short-time Fourier transform (STFT), which partitions the sequence into multiple subsequences and applies a Fourier transform to each separately. We propose the Frequency Information Aggregation (FIA)-Net, which is based on a novel complex-valued MLP architecture that aggregates adjacent window information in the frequency domain. To further increase the receptive field of the FIA-Net, we treat the set of windows as hyper-complex (HC) valued vectors and employ HC algebra to efficiently combine information from all STFT windows altogether. Using the HC-MLP backbone allows for improved handling of sequences with long-term dependence. Furthermore, due to the nature of HC operations, the HC-MLP uses up to three times fewer parameters than the equivalent standard window aggregation method. We evaluate the FIA-Net on various time-series benchmarks and show that the proposed methodologies outperform existing state of the art methods in terms of both accuracy and efficiency. Our code is publicly available on https://anonymous.4open.science/r/research-1803/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_19983 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Efficient Time Series Forecasting via Hyper-Complex Models and Frequency Aggregation Yakir, Eyal Tsur, Dor Permuter, Haim Machine Learning 62M20, 42A16, 68T05, 15A66 62M20, 42A16, 68T05, 15A66 62M20, 42A16, 68T05, 15A66 I.2.6; I.5.1 Time series forecasting is a long-standing problem in statistics and machine learning. One of the key challenges is processing sequences with long-range dependencies. To that end, a recent line of work applied the short-time Fourier transform (STFT), which partitions the sequence into multiple subsequences and applies a Fourier transform to each separately. We propose the Frequency Information Aggregation (FIA)-Net, which is based on a novel complex-valued MLP architecture that aggregates adjacent window information in the frequency domain. To further increase the receptive field of the FIA-Net, we treat the set of windows as hyper-complex (HC) valued vectors and employ HC algebra to efficiently combine information from all STFT windows altogether. Using the HC-MLP backbone allows for improved handling of sequences with long-term dependence. Furthermore, due to the nature of HC operations, the HC-MLP uses up to three times fewer parameters than the equivalent standard window aggregation method. We evaluate the FIA-Net on various time-series benchmarks and show that the proposed methodologies outperform existing state of the art methods in terms of both accuracy and efficiency. Our code is publicly available on https://anonymous.4open.science/r/research-1803/. |
| title | Efficient Time Series Forecasting via Hyper-Complex Models and Frequency Aggregation |
| topic | Machine Learning 62M20, 42A16, 68T05, 15A66 62M20, 42A16, 68T05, 15A66 62M20, 42A16, 68T05, 15A66 I.2.6; I.5.1 |
| url | https://arxiv.org/abs/2502.19983 |