Revitalizing Multivariate Time Series Forecasting: Learnable Decomposition with Inter-Series Dependencies and Intra-Series Variations Modeling

2024/02/20 by Guoqi Yu, Jing Zou, Yu, Guoqi +9 · 13 citations
Computer Science · Decision Sciences · #FOS: Computer and information sciences #Forecasting Techniques and Applications #Machine Learning (cs.LG) #Time Series Analysis and Forecasting

paper · pdf · doi:10.48550/arxiv.2402.12694

openalex publication_date 2024/02/20 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Predicting multivariate time series is crucial, demanding precise modeling of intricate patterns, including inter-series dependencies and intra-series variations. Distinctive trend characteristics in each time series pose challenges, and existing methods, relying on basic moving average kernels, may struggle with the non-linear structure and complex trends in real-world data. Given that, we introduce a learnable decomposition strategy to capture dynamic trend information more reasonably. Additionally, we propose a dual attention module tailored to capture inter-series dependencies and intra-series variations simultaneously for better time series forecasting, which is implemented by channel-wise self-attention and autoregressive self-attention. To evaluate the effectiveness of our method, we conducted experiments across eight open-source datasets and compared it with the state-of-the-art methods. Through the comparison results, our Leddam (LEarnable Decomposition and Dual Attention Module) not only demonstrates significant advancements in predictive performance, but also the proposed decomposition strategy can be plugged into other methods with a large performance-boosting, from 11.87% to 48.56% MSE error degradation.

Cited by

• SEED: Spectral Entropy-Guided Evaluation of SpatialTemporal Dependencies for Multivariate Time Series Forecasting
• EMAformer: Enhancing Transformer through Embedding Armor for Time Series Forecasting
• Ada-FCN: Adaptive Frequency-Coupled Network for fMRI-Based Brain Disorder Classification
• Inner-Instance Normalization for Time Series Forecasting
• HTMformer: Hybrid Time and Multivariate Transformer for Time Series Forecasting
• ReNF: Rethinking the Design of Neural Long-Term Time Series Forecasters
• Echo Flow Networks
• Channel, Trend and Periodic-Wise Representation Learning for Multivariate Long-term Time Series Forecasting
• Why Attention Fails: The Degeneration of Transformers into MLPs in Time Series Forecasting
• Bridging Past and Future: Distribution-Aware Alignment for Time Series Forecasting
• Dynamic Relational Priming Improves Transformer in Multivariate Time Series
• Filter then Attend: Improving attention-based Time Series Forecasting with Spectral Filtering
• HGTS-Former: Hierarchical HyperGraph Transformer for Multivariate Time Series Analysis

Related

• Expressing Multivariate Time Series as Graphs with Time Series Attention Transformer
• Channel, Trend and Periodic-Wise Representation Learning for Multivariate Long-term Time Series Forecasting
• Revisiting Attention for Multivariate Time Series Forecasting
• Parallel Extraction of Long-term Trends and Short-term Fluctuation Framework for Multivariate Time Series Forecasting
• KARMA: A Multilevel Decomposition Hybrid Mamba Framework for Multivariate Long-Term Time Series Forecasting