多尺度Mamba提升时间序列预测精度，参数更少、效率更高
ms-Mamba: Multi-scale Mamba for Time-Series Forecasting
- 用不同采样率的Mamba块并行处理多时间尺度信息
- 在太阳能数据集上误差低至0.229，优于同类模型
- 适合追求高效高精度时序预测的研究与工程应用
时间序列预测通常由循环网络、基于Transformer的模型以及近期提出的Mamba架构解决。然而，现有架构一般仅在单一时间尺度处理输入，对多尺度变化的任务可能不够理想。本文提出一种新架构ms-Mamba，通过引入多个具有不同采样率（Δ）的Mamba块来捕捉多尺度时间特征。大量基准测试表明，ms-Mamba超越了当前最先进方法，包括最新的Transformer和Mamba模型。例如，在Solar-Energy数据集上，ms-Mamba的均方误差为0.229，优于最近的S-Mamba（0.240），同时参数量更少（3.53M vs. 4.77M），内存占用更低（13.46MB vs. 18.18MB），计算量更小（14.93G vs. 20.53G MACs），平均覆盖四个预测长度。代码与模型将公开。
原文摘要 · Abstract (English)
The problem of Time-series Forecasting is generally addressed by recurrent, Transformer-based and the recently proposed Mamba-based architectures. However, existing architectures generally process their input at a single temporal scale, which may be sub-optimal for many tasks where information changes over multiple time scales. In this paper, we introduce a novel architecture called Multi-scale Mamba (ms-Mamba) to address this gap. ms-Mamba incorporates multiple temporal scales by using multiple Mamba blocks with different sampling rates ($Δ$s). Our experiments on many benchmarks demonstrate that ms-Mamba outperforms state-of-the-art approaches, including the recently proposed Transformer-based and Mamba-based models. For example, on the Solar-Energy dataset, ms-Mamba outperforms its closest competitor S-Mamba (0.229 vs. 0.240 in terms of mean-squared error) while using fewer parameters (3.53M vs. 4.77M), less memory (13.46MB vs. 18.18MB), and less operations (14.93G vs. 20.53G MACs), averaged across four forecast lengths. Codes and models will be made available.
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。