FreqFlow：基于轻量级流匹配的长期预测
摘要
多变量时间序列（Multivariate Time-Series, MTS）预测是涉及城市交通、资源管理和气候建模等应用的基本任务。虽然近期基于去噪扩散的生成模型在捕捉复杂数据分布方面取得了最新进展，但由于迭代随机抽样程序带来的计算开销，限制了实时部署。此外，这些模型在处理具有非平稳性和多尺度周期性特征的真实世界传感器网络时可能不够稳健。我们引入FreqFlow，一种新型框架，利用频域条件流匹配实现确定性MTS预测。不同于常规方法在时域中操作，FreqFlow将预测问题转换到频谱域，在该域上学习通过单个复值线性层建模振幅和相位偏移。这种频域表述使模型能够通过复数乘法高效捕捉时序动力学，对应于尺度和时序平移。 resulting architecture is exceptionally lightweight with only 89k parameters - an order of magnitude smaller than competing diffusion-based models-while enabling single-pass deterministic sampling through ordinary differential equation (ODE) integration. Our approach decomposes MTS signals into trend, seasonal, and residual components, with the flow matching mechanism specifically designed for residual learning to enhance long-term forecasting accuracy. Extensive experiments on real-world traffic speed, volume, and flow datasets demonstrate that FreqFlow achieves state-of-the-art forecasting performance, on average 7% RMSE improvements, while being significantly faster and more parameter-efficient than existing methods
引用
@article{arxiv.2511.16426,
title = {FreqFlow: Long-term forecasting using lightweight flow matching},
author = {Seyed Mohamad Moghadas and Bruno Cornelis and Adrian Munteanu},
journal= {arXiv preprint arXiv:2511.16426},
year = {2025}
}
备注
Accepted at EurIPS, 2025