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

arXiv: https://arxiv.org/abs/2201.04828 · HTML: https://mlsanity.com/paper/2201.04828/

## Key facts

- Cited by 42 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 48 references that are in the map.
- First posted on arXiv 13 Jan 2022.

## Builds on (most cited first, 23 of 23)

- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Graph Neural Networks: A Review of Methods and Applications](https://mlsanity.com/paper/1812.08434/) (2018)
- [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://mlsanity.com/paper/1602.07261/) (2016)
- [An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling](https://mlsanity.com/paper/1803.01271/) (2018)
- [Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks](https://mlsanity.com/paper/1703.07015/) (2017)
- [Graph WaveNet for Deep Spatial-Temporal Graph Modeling](https://mlsanity.com/paper/1906.00121/) (2019)
- [Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting](https://mlsanity.com/paper/1907.00235/) (2019)
- [Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks](https://mlsanity.com/paper/2005.11650/) (2020)
- [Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting](https://mlsanity.com/paper/2007.02842/) (2020)
- [GMAN: A Graph Multi-Attention Network for Traffic Prediction](https://mlsanity.com/paper/1911.08415/) (2019)
- [Neural Relational Inference for Interacting Systems](https://mlsanity.com/paper/1802.04687/) (2018)
- [Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting](https://mlsanity.com/paper/2103.07719/) (2021)
- [Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Prediction](https://mlsanity.com/paper/2111.00064/) (2021)
- [Temporal Pattern Attention for Multivariate Time Series Forecasting](https://mlsanity.com/paper/1809.04206/) (2018)
- [Multi-Range Attentive Bicomponent Graph Convolutional Network for Traffic Forecasting](https://mlsanity.com/paper/1911.12093/) (2019)
- [Learning Implicitly Recurrent CNNs Through Parameter Sharing](https://mlsanity.com/paper/1902.09701/) (2019)
- [Graph Attention Recurrent Neural Networks for Correlated Time Series Forecasting -- Full version](https://mlsanity.com/paper/2103.10760/) (2021)
- [A Memory-Network Based Solution for Multivariate Time-Series Forecasting](https://mlsanity.com/paper/1809.02105/) (2018)
- [Factorised Neural Relational Inference for Multi-Interaction Systems](https://mlsanity.com/paper/1905.08721/) (2019)
- [Variable-lag Granger Causality and Transfer Entropy for Time Series Analysis](https://mlsanity.com/paper/2002.00208/) (2020)
- [One Size Does Not Fit All: Multi-Scale, Cascaded RNNs for Radar Classification](https://mlsanity.com/paper/1909.03082/) (2019)
- [MTHetGNN: A Heterogeneous Graph Embedding Framework for Multivariate Time Series Forecasting](https://mlsanity.com/paper/2008.08617/) (2020)
- [Learning from Multiple Time Series: A Deep Disentangled Approach to Diversified Time Series Forecasting](https://mlsanity.com/paper/2111.04942/) (2021)

## Built on by (most cited first, 30 of 42)

- [Scaleformer: Iterative Multi-scale Refining Transformers for Time Series Forecasting](https://mlsanity.com/paper/2206.04038/) (2022)
- [Aurora: Towards Universal Generative Multimodal Time Series Forecasting](https://mlsanity.com/paper/2509.22295/) (2025)
- [Fully-Connected Spatial-Temporal Graph for Multivariate Time-Series Data](https://mlsanity.com/paper/2309.05305/) (2023)
- [Ada-MSHyper: Adaptive Multi-Scale Hypergraph Transformer for Time Series Forecasting](https://mlsanity.com/paper/2410.23992/) (2024)
- [LightCTS: A Lightweight Framework for Correlated Time Series Forecasting](https://mlsanity.com/paper/2302.11974/) (2023)
- [Graph-based Forecasting with Missing Data through Spatiotemporal Downsampling](https://mlsanity.com/paper/2402.10634/) (2024)
- [GCGNet: Graph-Consistent Generative Network for Time Series Forecasting with Exogenous Variables](https://mlsanity.com/paper/2603.08032/) (2026)
- [MSHyper: Multi-Scale Hypergraph Transformer for Long-Range Time Series Forecasting](https://mlsanity.com/paper/2401.09261/) (2024)
- [Enhancing the Robustness via Adversarial Learning and Joint Spatial-Temporal Embeddings in Traffic Forecasting](https://mlsanity.com/paper/2208.03063/) (2022)
- [A Systematic Literature Review of Spatio-Temporal Graph Neural Network Models for Time Series Forecasting and Classification](https://mlsanity.com/paper/2410.22377/) (2024)
- [ASTGI: Adaptive Spatio-Temporal Graph Interactions for Irregular Multivariate Time Series Forecasting](https://mlsanity.com/paper/2509.23313/) (2025)
- [ADEdgeDrop: Adversarial Edge Dropping for Robust Graph Neural Networks](https://mlsanity.com/paper/2403.09171/) (2024)
- [Nearest Neighbor Multivariate Time Series Forecasting](https://mlsanity.com/paper/2505.11625/) (2025)
- [OKG-LLM: Aligning Ocean Knowledge Graph with Observation Data via LLMs for Global Sea Surface Temperature Prediction](https://mlsanity.com/paper/2508.00933/) (2025)
- [Graph Generation Powered with LLMs for Boosting Multivariate Time-Series Representation Learning](https://mlsanity.com/paper/2403.03645/) (2024)
- [Spatial-Temporal Mixture-of-Graph-Experts for Multi-Type Crime Prediction](https://mlsanity.com/paper/2409.15764/) (2024)
- [MSDformer: Multi-scale Discrete Transformer For Time Series Generation](https://mlsanity.com/paper/2505.14202/) (2025)
- [D-PAD: Deep-Shallow Multi-Frequency Patterns Disentangling for Time Series Forecasting](https://mlsanity.com/paper/2403.17814/) (2024)
- [DuoGNN: Topology-aware Graph Neural Network with Homophily and Heterophily Interaction-Decoupling](https://mlsanity.com/paper/2409.19616/) (2024)
- [Multi-scale hypergraph meets LLMs: Aligning large language models for time series analysis](https://mlsanity.com/paper/2602.04369/) (2026)
- [Exploiting Individual Graph Structures to Enhance Ecological Momentary Assessment (EMA) Forecasting](https://mlsanity.com/paper/2403.19442/) (2024)
- [Temporal and Heterogeneous Graph Neural Network for Remaining Useful Life Prediction](https://mlsanity.com/paper/2405.04336/) (2024)
- [FAITH: Frequency-domain Attention In Two Horizons for Time Series Forecasting](https://mlsanity.com/paper/2405.13300/) (2024)
- [Leveraging Multivariate Long-Term History Representation for Time Series Forecasting](https://mlsanity.com/paper/2505.14737/) (2025)
- [Beyond All-to-All: Causal-Aligned Transformer with Dynamic Structure Learning for Multivariate Time Series Forecasting](https://mlsanity.com/paper/2505.16308/) (2025)
- [Mixture of Low Rank Adaptation with Partial Parameter Sharing for Time Series Forecasting](https://mlsanity.com/paper/2505.17872/) (2025)
- [TimeFormer: Transformer with Attention Modulation Empowered by Temporal Characteristics for Time Series Forecasting](https://mlsanity.com/paper/2510.06680/) (2025)
- [Nested Spatio-Temporal Time Series Forecasting](https://mlsanity.com/paper/2605.16447/) (2026)
- [FlightPatchNet: Multi-Scale Patch Network with Differential Coding for Flight Trajectory Prediction](https://mlsanity.com/paper/2405.16200/) (2024)
- [Optimizing Sales Forecasts through Automated Integration of Market Indicators](https://mlsanity.com/paper/2406.07564/) (2024)

## Abstract (arXiv)

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.