A Decomposition-based State Space Model for Multivariate Time-Series Forecasting

📅 2026-02-05
📈 Citations: 0
Influential: 0
📄 PDF

career value

219K/year
🤖 AI Summary
This work addresses the challenge of modeling highly coupled trend, multi-scale seasonal, and irregular residual components in multivariate time series forecasting, where cross-variable shared structures are difficult to capture effectively. To this end, the authors propose DecompSSM, a novel framework that employs three parallel deep state space model branches to explicitly learn trend, seasonality, and residual components. The approach integrates a learnable decomposition mechanism, an input-dependent adaptive temporal scale predictor, a cross-variable context refinement module, and an orthogonality-constrained auxiliary loss to enable end-to-end structure-aware disentangled modeling. Extensive experiments demonstrate that DecompSSM significantly outperforms strong baselines on benchmark datasets including ECL, Weather, ETTm2, and PEMS04, validating the effectiveness of component-wise state space modeling combined with global context refinement.

Technology Category

Application Category

📝 Abstract
Multivariate time series (MTS) forecasting is crucial for decision-making in domains such as weather, energy, and finance. It remains challenging because real-world sequences intertwine slow trends, multi-rate seasonalities, and irregular residuals. Existing methods often rely on rigid, hand-crafted decompositions or generic end-to-end architectures that entangle components and underuse structure shared across variables. To address these limitations, we propose DecompSSM, an end-to-end decomposition framework using three parallel deep state space model branches to capture trend, seasonal, and residual components. The model features adaptive temporal scales via an input-dependent predictor, a refinement module for shared cross-variable context, and an auxiliary loss that enforces reconstruction and orthogonality. Across standard benchmarks (ECL, Weather, ETTm2, and PEMS04), DecompSSM outperformed strong baselines, indicating the effectiveness of combining component-wise deep state space models and global context refinement.
Problem

Research questions and friction points this paper is trying to address.

multivariate time series forecasting
time series decomposition
trend-seasonality-residual entanglement
cross-variable structure
state space model
Innovation

Methods, ideas, or system contributions that make the work stand out.

Decomposition
State Space Model
Multivariate Time Series Forecasting
Adaptive Temporal Scales
Cross-variable Context
🔎 Similar Papers
No similar papers found.