MSMixer通过多尺度混合提升长时序预测精度，参数少、速度快。
MSMixer: Learned Multi-Scale Temporal Mixing with Complementary Linear Shortcut for Long-Term Time Series Forecasting
- 设计三路并行多尺度分支，分别处理不同时间粒度的特征。
- 在四个数据集上平均误差0.357，优于DLinear和NLinear。
- 适合追求轻量化与高精度的长时序预测场景。
长时序时间序列预测需同时捕捉快速波动、中等周期和缓慢宏观趋势，现有轻量级MLP模型通常仅在单一时间分辨率下运行，难以显式建模多尺度模式。我们提出MSMixer，一种通道无关的多尺度MLP架构，通过三项互补创新解决此问题：(i) 在下采样因子{1x, 4x, 16x}处设置三路并行分支，各自配备独立MLP块；(ii) 可学习的softmax门控动态加权分支输出；(iii) DLinear互补捷径提供全窗口趋势与季节性上下文。MSMixer在H=96时仅含112K参数，计算复杂度为O(T)。在四个ETT基准上采用标准时序划分与三个随机种子评估，其平均MSE（0.357）为轻量级模型最低，优于DLinear（0.386，-7.4%）和NLinear（0.365，-2.1%），在16组配置中胜出12次。相比五种基于Transformer的基线模型，它在16组中的9组取得最佳或第二佳性能，参数量仅为PatchTST的1/5。消融与敏感性分析验证了多尺度分支与DLinear捷径的互补作用。
原文摘要 · Abstract (English)
Long-term time series forecasting requires models that simultaneously capture rapid oscillations, medium-range periodicities, and slowly evolving macro-trends from a fixed look-back window. Existing lightweight MLP-based models typically operate on a single temporal resolution, limiting their ability to explicitly model patterns at multiple scales. We propose MSMixer, a channel-independent multi-scale MLP architecture that addresses this limitation through three complementary innovations: (i) three parallel scale branches at down-sample factors {1x, 4x, 16x} with independent MLP blocks, (ii) a learnable softmax gate that dynamically weighs branch outputs, and (iii) a DLinear complementary shortcut that provides full-window trend and seasonality context. MSMixer contains only 112K parameters at H=96 and runs at O(T) complexity. Evaluated on four ETT benchmarks with standard chronological splits and three random seeds, MSMixer achieves the lowest average MSE (0.357) among lightweight models, outperforming DLinear (0.386, -7.4%) and NLinear (0.365, -2.1%), winning 12 of 16 configurations. Against five Transformer-based baselines from the literature, MSMixer achieves best or second-best MSE in 9 of 16 configurations while using 5x fewer parameters than PatchTST. Ablation and sensitivity analyses confirm the complementary contributions of the multi-scale branches and the DLinear shortcut.
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。