Multi-Scale Adaptive Graph Neural Network for Multivariate Time Series Forecasting

2022/01/13 by Ling Chen, Chen, Ling, Donghui Chen +8 · 13 citations
Computer Science · Decision Sciences · Mathematics · #Artificial intelligence #Artificial neural network #Computer science #Data mining #Exploit #Feature (linguistics) #Graph #Machine learning #Mathematics #Neural Networks and Applications #Scale (ratio) #Stock Market Forecasting Methods #Theoretical computer science #Time Series Analysis and Forecasting #Time series #Variable (mathematics)

paper · pdf · doi:10.48550/arxiv.2201.04828

published in arXiv (Cornell University) (Cornell University)

openalex publication_date 2022/01/13 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05

Abstract

Multivariate time series (MTS) forecasting plays an important role in the automation and optimization of intelligent applications. It is a challenging task, as we need to consider both complex intra-variable dependencies and inter-variable dependencies. Existing works only learn temporal patterns with the help of single inter-variable dependencies. However, there are multi-scale temporal patterns in many real-world MTS. Single inter-variable dependencies make the model prefer to learn one type of prominent and shared temporal patterns. In this paper, we propose a multi-scale adaptive graph neural network (MAGNN) to address the above issue. MAGNN exploits a multi-scale pyramid network to preserve the underlying temporal dependencies at different time scales. Since the inter-variable dependencies may be different under distinct time scales, an adaptive graph learning module is designed to infer the scale-specific inter-variable dependencies without pre-defined priors. Given the multi-scale feature representations and scale-specific inter-variable dependencies, a multi-scale temporal graph neural network is introduced to jointly model intra-variable dependencies and inter-variable dependencies. After that, we develop a scale-wise fusion module to effectively promote the collaboration across different time scales, and automatically capture the importance of contributed temporal patterns. Experiments on four real-world datasets demonstrate that MAGNN outperforms the state-of-the-art methods across various settings.

Cited by

• Impute On-Demand: Adaptive Correlated Time Series Imputation for Changing Environments
• Multivariate Time Series Forecasting with Hybrid Euclidean-SPD Manifold Graph Neural Networks
• TimeFormer: Transformer with Attention Modulation Empowered by Temporal Characteristics for Time Series Forecasting
• Echo Flow Networks
• Graph Neural Networks with Diversity-aware Neighbor Selection and Dynamic Multi-scale Fusion for Multivariate Time Series Forecasting
• ASTGI: Adaptive Spatio-Temporal Graph Interactions for Irregular Multivariate Time Series Forecasting
• Aurora: Towards Universal Generative Multimodal Time Series Forecasting
• OKG-LLM: Aligning Ocean Knowledge Graph with Observation Data via LLMs for Global Sea Surface Temperature Prediction
• Mixture of Low Rank Adaptation with Partial Parameter Sharing for Time Series Forecasting
• Beyond All-to-All: Causal-Aligned Transformer with Dynamic Structure Learning for Multivariate Time Series Forecasting
• MSDformer: Multi-scale Discrete Transformer For Time Series Generation
• Leveraging Multivariate Long-Term History Representation for Time Series Forecasting
• Nearest Neighbor Multivariate Time Series Forecasting

Related

• Learning the Evolutionary and Multi-scale Graph Structure for Multivariate Time Series Forecasting
• Scale-Aware Neural Architecture Search for Multivariate Time Series Forecasting
• Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks
• Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks
• ForecastGrapher: Redefining Multivariate Time Series Forecasting with Graph Neural Networks