UniMamba: A Unified Spatial-Temporal Modeling Framework with State-Space and Attention Integration

TL;DR

UniMamba is a novel unified framework combining state-space models and attention mechanisms to improve multivariate time series forecasting accuracy and efficiency across various domains.

Contribution

It introduces a new integrated model that combines FFT-Laplace Transform, TCN, and spatial-temporal attention for enhanced long-sequence forecasting.

Findings

Outperforms existing models in accuracy on eight datasets.

Achieves better computational efficiency than traditional Transformer-based methods.

Demonstrates robustness and scalability for multivariate time series prediction.

Abstract

Multivariate time series forecasting is fundamental to numerous domains such as energy, finance, and environmental monitoring, where complex temporal dependencies and cross-variable interactions pose enduring challenges. Existing Transformer-based methods capture temporal correlations through attention mechanisms but suffer from quadratic computational cost, while state-space models like Mamba achieve efficient long-context modeling yet lack explicit temporal pattern recognition. Therefore we introduce UniMamba, a unified spatial-temporal forecasting framework that integrates efficient state-space dynamics with attention-based dependency learning. UniMamba employs a Mamba Variate-Channel Encoding Layer enhanced with FFT-Laplace Transform and TCN to capture global temporal dependencies, and a Spatial Temporal Attention Layer to jointly model inter-variate correlations and temporal evolution. A Feedforward Temporal Dynamics Layer further fuses continuous and discrete contexts for accurate forecasting. Comprehensive experiments on eight public benchmark datasets demonstrate that UniMamba consistently outperforms state-of-the-art forecasting models in both forecasting accuracy and computational efficiency, establishing a scalable and robust solution for long-sequence multivariate time-series prediction.