通过频域分解专家模型提升时间序列预测精度与效率
FreqMoE: Enhancing Time Series Forecasting through Frequency Decomposition Mixture of Experts
- 将时序数据按频率分 band，由不同专家分别处理
- 在70个指标中51项超越顶尖模型，参数少于5万
- 适合需要高精度低资源的时序预测场景
长期时间序列预测在金融和天气预报等领域至关重要。尽管传统方法在时域操作，近年许多模型将时序数据转换到频域以捕捉复杂模式，但常使用滤波技术去除某些频率信号作为噪声，可能无意中丢弃重要信息，降低预测准确率。为此，我们提出频率分解混合专家（FreqMoE）模型，动态将时序数据分解为频率带，每一带由专用专家处理。门控机制根据频率特征调整各专家输出的重要性，聚合结果经残差连接迭代优化后输入预测模块。实验表明，FreqMoE 在所有测试数据集上 70 个指标中有 51 项优于现有最先进模型，同时参数量显著低于 50,000，展现出明显效率优势。代码已开源：https://github.com/sunbus100/FreqMoE-main
原文摘要 · Abstract (English)
Long-term time series forecasting is essential in areas like finance and weather prediction. Besides traditional methods that operate in the time domain, many recent models transform time series data into the frequency domain to better capture complex patterns. However, these methods often use filtering techniques to remove certain frequency signals as noise, which may unintentionally discard important information and reduce prediction accuracy. To address this, we propose the Frequency Decomposition Mixture-of-Experts (FreqMoE) model, which dynamically decomposes time series data into frequency bands, each processed by a specialized expert. A gating mechanism adjusts the importance of each output of expert based on frequency characteristics, and the aggregated results are fed into a prediction module that iteratively refines the forecast using residual connections. Our experiments demonstrate that FreqMoE outperforms state-of-the-art models, achieving the best performance on 51 out of 70 metrics across all tested datasets, while significantly reducing the number of required parameters to under 50k, providing notable efficiency advantages. Code is available at: https://github.com/sunbus100/FreqMoE-main
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。