DMamba: Decomposition-enhanced Mamba for Time Series Forecasting

TL;DR

DMamba introduces a decomposition-aware architecture for time series forecasting, employing specialized modules for trend and seasonal components, leading to state-of-the-art results across diverse datasets.

Contribution

It proposes DMamba, a novel model that explicitly aligns architectural complexity with trend and seasonal components, improving long-term forecasting accuracy.

Findings

DMamba outperforms recent Mamba-based architectures.

The model achieves state-of-the-art results on multiple datasets.

Component-specific processing enhances forecasting performance.

Abstract

State Space Models (SSMs), particularly Mamba, have shown potential in long-term time series forecasting. However, existing Mamba-based architectures often struggle with datasets characterized by non-stationary patterns. A key observation from time series theory is that the statistical nature of inter-variable relationships differs fundamentally between the trend and seasonal components of a decomposed series. Trend relationships are often driven by a few common stochastic factors or long-run equilibria, suggesting that they reside on a lower-dimensional manifold. In contrast, seasonal relationships involve dynamic, high-dimensional interactions like phase shifts and amplitude co-movements, requiring more expressive modeling. In this paper, we propose DMamba, a novel forecasting model that explicitly aligns architectural complexity with this component-specific characteristic. DMamba employs seasonal-trend decomposition and processes the components with specialized, differentially complex modules: a variable-direction Mamba encoder captures the rich, cross-variable dynamics within the seasonal component, while a simple Multi-Layer Perceptron (MLP) suffices to learn from the lower-dimensional inter-variable relationships in the trend component. Extensive experiments on diverse datasets demonstrate that DMamba sets a new state-of-the-art (SOTA), consistently outperforming both recent Mamba-based architectures and leading decomposition-based models.