Title of Paper:DualMamba: Patch-Based Model with Dual Mamba for Long-Term Time Series Forecasting

Hits:

Journal:Frontiers of Computer Science

Key Words:Long-term time series forecasting, State Space Model, Mamba, Patching

Abstract:The field of time series forecasting has
been seen widespread application of Transformerbased architectures. However, the quadratic complexity of the attention mechanism limits its performance in long-term time series forecasting. The
proposition of patching mechanism has alleviated
this issue to some extent, but models will struggle
to effectively unify the information between intrapatch and inter-patch . To address this problem, we
propose DualMamba, a novel Mamba-based model
for time series forecasting, which segments the time
series into subseries-level patches and employs dual
Mamba modules to capture local and global information separately. Specifically, the time series use
patch-wise dependencies to guide the local module, where each patch uses a point-wise representation of time series data. Furthermore, we designed a information fusion mechanism for integrating information between intra-patch and interpatch, which effectively incorporates global information into local contexts. This allows the model
to capture both local details and global trends. Extensive experiments on several real-world datasets
demonstrate that DualMamba achieves state-of-theart performance in most cases and has reliable robustness, making it highly adaptable for various
types of time series.

Translation or Not:no

Included Journals:SCI

Correspondence Author:冯爱民