arXiv 2604.279812026-04-30cs.LGcs.AI

ITS-Mina：一种基于Harris Hawks优化的全MLP框架，结合迭代细化和外部注意力机制用于多变量时间序列预测

ITS-Mina: A Harris Hawks Optimization-Based All-MLP Framework with Iterative Refinement and External Attention for Multivariate Time Series Forecasting

Department of Computer Science and Engineering, Shahid Beheshti University, Iran（伊朗谢赫·贝赫什提大学计算机科学与工程系）；School of Computer Science, Institute for Research in Fundamental Sciences (IPM), Iran（伊朗基础科学研究院（IPM）计算机科学学院）

Pourya Zamanvaziri, Amirhossein Sadr, Aida Pakniyat, Dara Rahmati

备注：: 19 pages, 2 figures, 3 tables, 4 algorithms

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出ITS-Mina，一种全MLP框架，通过迭代细化机制、外部注意力模块和Harris Hawks优化算法，实现多变量时间序列预测的高精度与低计算成本。

摘要：

多变量时间序列预测在金融分析、能源管理和交通规划等实际应用中起着关键作用。虽然基于Transformer的架构在该任务中变得流行，但最近的研究表明，更简单的MLP模型可以在显著减少计算成本的情况下实现竞争性或更优的性能。在本文中，我们提出了ITS-Mina，一种新的全MLP框架，用于多变量时间序列预测，集成了三个关键创新：(1) 一个迭代细化机制，通过反复应用共享参数残差混合堆栈逐步增强时间表示，有效加深模型的计算能力而不增加不同参数的数量；(2) 一个外部注意力模块，用可学习的记忆单元取代传统的自注意力，以线性计算复杂度捕获跨样本的全局依赖关系；(3) 一种Harris Hawks优化（HHO）算法用于自动调整dropout率，使正则化能够适应每个数据集。在六个广泛使用的基准数据集上的大量实验表明，ITS-Mina在多个预测时间范围内相比十一种基线模型实现了最先进的或高度竞争的性能。

英文摘要：

Multivariate time series forecasting plays a pivotal role in numerous real-world applications, including financial analysis, energy management, and traffic planning. While Transformer-based architectures have gained popularity for this task, recent studies reveal that simpler MLP-based models can achieve competitive or superior performance with significantly reduced computational cost. In this paper, we propose ITS-Mina, a novel all-MLP framework for multivariate time series forecasting that integrates three key innovations: (1) an iterative refinement mechanism that progressively enhances temporal representations by repeatedly applying a shared-parameter residual mixer stack, effectively deepening the model's computational capacity without multiplying the number of distinct parameters; (2) an external attention module that replaces traditional self-attention with learnable memory units, capturing cross-sample global dependencies at linear computational complexity; and (3) a Harris Hawks Optimization (HHO) algorithm for automatic dropout rate tuning, enabling adaptive regularization tailored to each dataset. Extensive experiments on six widely-used benchmark datasets demonstrate that ITS-Mina achieves state-of-the-art or highly competitive performance compared to eleven baseline models across multiple forecasting horizons.

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。