ASGMamba: Adaptive Spectral Gating Mamba for Multivariate Time Series Forecasting

TL;DR

ASGMamba is a scalable, resource-efficient multivariate time series forecasting framework that combines adaptive spectral gating with a hierarchical architecture to improve accuracy and reduce memory usage in long-horizon predictions.

Contribution

It introduces a novel adaptive spectral gating mechanism and a hierarchical multi-scale architecture to enhance long-term forecasting efficiency and accuracy in resource-constrained environments.

Findings

Achieves state-of-the-art accuracy on nine benchmarks.

Maintains linear complexity while reducing memory usage.

Effective noise filtering improves signal quality.

Abstract

Long-term multivariate time series forecasting (LTSF) plays a crucial role in various high-performance computing applications, including real-time energy grid management and large-scale traffic flow simulation. However, existing solutions face a dilemma: Transformer-based models suffer from quadratic complexity, limiting their scalability on long sequences, while linear State Space Models (SSMs) often struggle to distinguish valuable signals from high-frequency noise, leading to wasted state capacity. To bridge this gap, we propose ASGMamba, an efficient forecasting framework designed for resource-constrained supercomputing environments. ASGMamba integrates a lightweight Adaptive Spectral Gating (ASG) mechanism that dynamically filters noise based on local spectral energy, enabling the Mamba backbone to focus its state evolution on robust temporal dynamics. Furthermore, we introduce a hierarchical multi-scale architecture with variable-specific Node Embeddings to capture diverse physical characteristics. Extensive experiments on nine benchmarks demonstrate that ASGMamba achieves state-of-the-art accuracy. While keeping strictly $$\mathcal{O}(L)$$ complexity we significantly reduce the memory usage on long-horizon tasks, thus establishing ASGMamba as a scalable solution for high-throughput forecasting in resource limited environments.The code is available at https://github.com/hit636/ASGMamba