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

TL;DR

ITS-Mina introduces an all-MLP framework with iterative refinement, external attention, and HHO-based regularization, achieving state-of-the-art multivariate time series forecasting with reduced computational cost.

Contribution

The paper presents a novel all-MLP architecture with iterative refinement, external attention, and HHO optimization, offering a new efficient approach for multivariate time series forecasting.

Findings

Achieves state-of-the-art performance on six benchmark datasets.

Outperforms eleven baseline models across multiple forecasting horizons.

Demonstrates effectiveness of external attention and iterative refinement in MLP models.

Abstract

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.