FlowState能自动适应不同采样率，无需重训即可跨时间尺度预测。
FlowState: Sampling-Rate-Equivariant Time-Series Forecasting
- 用状态空间模型+函数基解码器实现连续时间建模，支持动态调整时间尺度。
- 在GIFT-Eval上表现超越现有模型，且对未见采样率有强泛化能力。
- 模型小巧高效，适合实际部署，尤其适合多采样率场景的预测任务。
现有时间序列基础模型（TSFMs）通常基于Transformer变体，缺乏对不同采样率的适应性，跨上下文与目标长度的泛化能力差，且计算效率低。我们提出FlowState，一种新型TSFM架构，通过统一设计将状态空间模型（SSM）编码器与函数基解码器（FBD）结合，实现采样率等变的时间序列预测。该设计支持连续时间建模和动态时间尺度调整，使FlowState能天然地在所有可能的时间分辨率间泛化，并在不重训的情况下动态调整预测时长。我们还提出一种高效的预训练策略，提升了鲁棒性并加速了训练过程。尽管是目前最小的TSFM之一，FlowState在广泛使用的GIFT-Eval基准上达到顶尖性能，同时展现出对未见采样率的卓越适应能力。详细分析验证了各组件的有效性，并证明其独特的时间采样率自适应能力。
原文摘要 · Abstract (English)
Existing time series foundation models (TSFMs), often based on transformer variants, lack adaptability to different sampling rates, struggle with generalization across varying context and target lengths, and are computationally inefficient. We introduce FlowState, a novel TSFM architecture that achieves sampling-rate-equivariant forecasting through a unified design that pairs a state space model (SSM) encoder with a functional basis decoder (FBD). This design enables continuous-time modeling and dynamic time-scale adjustment, allowing FlowState to inherently generalize across all possible temporal resolutions, and dynamically adjust the forecasting horizons without retraining. We further propose an efficient pretraining strategy that improves robustness and accelerates training. Despite being one of the smallest TSFMs, FlowState achieves state-of-the-art results on the widely used GIFT-Eval benchmark, while demonstrating superior adaptability to unseen sampling rates. Our detailed analyses confirm the effectiveness of its components, and we demonstrate its unique ability to adapt to varying input sampling rates.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。