MSAR: Next-Scale Autoregressive Forecasting for Time Series via Modular Multi-Scale Decoupling
Time series forecasting underpins critical applications in finance, energy, healthcare, and transportation. Although deep models have achieved strong results, most adopt single-scale modeling or restrict multiscale processing to the input side, causing a misalignment between multiscale inputs and single-scale outputs and limiting predictive power. We introduce the Modular Scale-wise Autoregressive Framework (MSAR), a model-agnostic design that forecasts progressively across multiple temporal resolutions. MSAR offers three advantages: (1) scale-wise aligned modeling, which disentangles heterogeneous temporal patterns by aligning inputs and outputs at each scale; (2) scale-wise autoregression, where coarse-scale predictions guide finer-scale forecasting through hierarchical information flow; and (3) a modular architecture, enabling seamless integration with diverse backbones such as CNNs, MLPs, and Transformers. Extensive experiments across a broad set of datasets and forecasting models demonstrate that MSAR achieves consistent improvements in both accuracy and inference efficiency, validating the effectiveness of scale-aligned autoregression for multiscale time series forecasting. The code is available at: https://github.com/Oryxo/MSAR.
Authors
- Fanda Fan (ORCID: https://orcid.org/0000-0002-5214-0959)
- Jianfeng Zhan (ORCID: https://orcid.org/0000-0002-3728-6837)
- Kuiye Ding (ORCID: https://orcid.org/0009-0007-1717-7733)
- Ruijie Jian (ORCID: https://orcid.org/0009-0004-7493-8920)
- LiMing Mao
- Bingsong Wang
- Chunjie Luo
- Yao Wang
- Xiaorui Wang
- Zhenghua Lu
- Zhipeng Liu
- Luqi Gong
Publication Details
- Journal
- arXiv (Cornell University)
- Published
- 2026-11-16
- DOI
- https://doi.org/10.48550/arxiv.2611.20714
- Primary Topic
- Time Series Analysis and Forecasting
- Type
- preprint