OneCast: Structured Decomposition and Modular Generation for Cross-Domain Time Series Forecasting
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_ | 1866908624304996352 |
|---|---|
| author | Pan, Tingyue Cheng, Mingyue Zhang, Shilong Liu, Zhiding Tao, Xiaoyu Luo, Yucong Zhang, Jintao Liu, Qi |
| author_facet | Pan, Tingyue Cheng, Mingyue Zhang, Shilong Liu, Zhiding Tao, Xiaoyu Luo, Yucong Zhang, Jintao Liu, Qi |
| contents | Cross-domain time series forecasting is a valuable task in various web applications. Despite its rapid advancement, achieving effective generalization across heterogeneous time series data remains a significant challenge. Existing methods have made progress by extending single-domain models, yet often fall short when facing domain-specific trend shifts and inconsistent periodic patterns. We argue that a key limitation lies in treating temporal series as undifferentiated sequence, without explicitly decoupling their inherent structural components. To address this, we propose OneCast, a structured and modular forecasting framework that decomposes time series into seasonal and trend components, each modeled through tailored generative pathways. Specifically, the seasonal component is captured by a lightweight projection module that reconstructs periodic patterns via interpretable basis functions. In parallel, the trend component is encoded into discrete tokens at segment level via a semantic-aware tokenizer, and subsequently inferred through a masked discrete diffusion mechanism. The outputs from both branches are combined to produce a final forecast that captures seasonal patterns while tracking domain-specific trends. Extensive experiments across eight domains demonstrate that OneCast mostly outperforms state-of-the-art baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_24028 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | OneCast: Structured Decomposition and Modular Generation for Cross-Domain Time Series Forecasting Pan, Tingyue Cheng, Mingyue Zhang, Shilong Liu, Zhiding Tao, Xiaoyu Luo, Yucong Zhang, Jintao Liu, Qi Artificial Intelligence Cross-domain time series forecasting is a valuable task in various web applications. Despite its rapid advancement, achieving effective generalization across heterogeneous time series data remains a significant challenge. Existing methods have made progress by extending single-domain models, yet often fall short when facing domain-specific trend shifts and inconsistent periodic patterns. We argue that a key limitation lies in treating temporal series as undifferentiated sequence, without explicitly decoupling their inherent structural components. To address this, we propose OneCast, a structured and modular forecasting framework that decomposes time series into seasonal and trend components, each modeled through tailored generative pathways. Specifically, the seasonal component is captured by a lightweight projection module that reconstructs periodic patterns via interpretable basis functions. In parallel, the trend component is encoded into discrete tokens at segment level via a semantic-aware tokenizer, and subsequently inferred through a masked discrete diffusion mechanism. The outputs from both branches are combined to produce a final forecast that captures seasonal patterns while tracking domain-specific trends. Extensive experiments across eight domains demonstrate that OneCast mostly outperforms state-of-the-art baselines. |
| title | OneCast: Structured Decomposition and Modular Generation for Cross-Domain Time Series Forecasting |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2510.24028 |