ISMRNN:一种结合 Mamba 的隐式分段 RNN 长期时间序列预测方法
ISMRNN: An Implicitly Segmented RNN Method with Mamba for Long-Term Time Series Forecasting
AI总结:
针对 SegRNN 固定分段破坏连续性、跨段信息利用不足及循环信息丢失问题,本文提出 ISMRNN,融合隐式分段、残差编码与 Mamba,在多个真实数据集上超过现有最先进模型。
摘要:
长期时间序列预测旨在利用历史信息,对更长时间范围内的未来状态进行预测。传统的基于 RNN 的序列预测方法难以有效解决长时间序列问题中的长期依赖和梯度问题。近年来,SegRNN 已成为面向长期序列预测的领先 RNN 模型,它通过创新的分段和并行解码技术,在保持精简架构的同时展现出最先进性能。然而,SegRNN 仍存在若干局限:其固定分段会破坏数据连续性,且无法有效利用不同分段之间的信息;SegRNN 采用的分段策略也没有从根本上解决循环结构中的信息丢失问题。为解决这些问题,我们提出 ISMRNN 方法,包含三项关键改进:引入隐式分段结构来分解时间序列并将其映射到分段隐状态,从而在分段阶段实现更密集的信息交换;此外,在编码层加入残差结构,以缓解循环结构内的信息丢失;为更有效地提取信息,进一步集成 Mamba 架构以增强时间序列信息提取能力。在多个真实世界长期时间序列预测数据集上的实验表明,我们的模型性能超越了当前最先进模型。
英文摘要:
Long time series forecasting aims to utilize historical information to forecast future states over extended horizons. Traditional RNN-based series forecasting methods struggle to effectively address long-term dependencies and gradient issues in long time series problems. Recently, SegRNN has emerged as a leading RNN-based model tailored for long-term series forecasting, demonstrating state-of-the-art performance while maintaining a streamlined architecture through innovative segmentation and parallel decoding techniques. Nevertheless, SegRNN has several limitations: its fixed segmentation disrupts data continuity and fails to effectively leverage information across different segments, the segmentation strategy employed by SegRNN does not fundamentally address the issue of information loss within the recurrent structure. To address these issues, we propose the ISMRNN method with three key enhancements: we introduce an implicit segmentation structure to decompose the time series and map it to segmented hidden states, resulting in denser information exchange during the segmentation phase. Additionally, we incorporate residual structures in the encoding layer to mitigate information loss within the recurrent structure. To extract information more effectively, we further integrate the Mamba architecture to enhance time series information extraction. Experiments on several real-world long time series forecasting datasets demonstrate that our model surpasses the performance of current state-of-the-art models.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。