# Graph Attention Recurrent Neural Networks for Correlated Time Series Forecasting -- Full version

arXiv: https://arxiv.org/abs/2103.10760 · HTML: https://mlsanity.com/paper/2103.10760/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 37 references that are in the map.
- First posted on arXiv 19 Mar 2021.

## Builds on (most cited first, 11 of 11)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting](https://mlsanity.com/paper/1709.04875/) (2017)
- [Spectral Networks and Locally Connected Networks on Graphs](https://mlsanity.com/paper/1312.6203/) (2013)
- [GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs](https://mlsanity.com/paper/1803.07294/) (2018)
- [GeniePath: Graph Neural Networks with Adaptive Receptive Paths](https://mlsanity.com/paper/1802.00910/) (2018)
- [Learning to Route with Sparse Trajectory Sets---Extended Version](https://mlsanity.com/paper/1802.07980/) (2018)

## Built on by (most cited first, 24 of 24)

- [TFB: Towards Comprehensive and Fair Benchmarking of Time Series Forecasting Methods](https://mlsanity.com/paper/2403.20150/) (2024)
- [A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detection](https://mlsanity.com/paper/2307.03759/) (2023)
- [Towards Spatio-Temporal Aware Traffic Time Series Forecasting--Full Version](https://mlsanity.com/paper/2203.15737/) (2022)
- [Triformer: Triangular, Variable-Specific Attentions for Long Sequence Multivariate Time Series Forecasting--Full Version](https://mlsanity.com/paper/2204.13767/) (2022)
- [AutoCTS: Automated Correlated Time Series Forecasting -- Extended Version](https://mlsanity.com/paper/2112.11174/) (2021)
- [Multi-Scale Adaptive Graph Neural Network for Multivariate Time Series Forecasting](https://mlsanity.com/paper/2201.04828/) (2022)
- [Unsupervised Time Series Outlier Detection with Diversity-Driven Convolutional Ensembles -- Extended Version](https://mlsanity.com/paper/2111.11108/) (2021)
- [Towards a General Time Series Forecasting Model with Unified Representation and Adaptive Transfer](https://mlsanity.com/paper/2405.17478/) (2024)
- [MST-GAT: A Multimodal Spatial-Temporal Graph Attention Network for Time Series Anomaly Detection](https://mlsanity.com/paper/2310.11169/) (2023)
- [Robust and Explainable Autoencoders for Unsupervised Time Series Outlier Detection---Extended Version](https://mlsanity.com/paper/2204.03341/) (2022)
- [Fully Automated Correlated Time Series Forecasting in Minutes](https://mlsanity.com/paper/2411.05833/) (2024)
- [CrossAD: Time Series Anomaly Detection with Cross-scale Associations and Cross-window Modeling](https://mlsanity.com/paper/2510.12489/) (2025)
- [AutoHFormer: Efficient Hierarchical Autoregressive Transformer for Time Series Prediction](https://mlsanity.com/paper/2506.16001/) (2025)
- [Graph Convolutional Networks for Traffic Forecasting with Missing Values](https://mlsanity.com/paper/2212.06419/) (2022)
- [QCore: Data-Efficient, On-Device Continual Calibration for Quantized Models -- Extended Version](https://mlsanity.com/paper/2404.13990/) (2024)
- [Orca: Ocean Significant Wave Height Estimation with Spatio-temporally Aware Large Language Models](https://mlsanity.com/paper/2407.20053/) (2024)
- [Unlocking the Value of Text: Event-Driven Reasoning and Multi-Level Alignment for Time Series Forecasting](https://mlsanity.com/paper/2603.15452/) (2026)
- [Towards Measuring and Modeling Geometric Structures in Time Series Forecasting via Image Modality](https://mlsanity.com/paper/2507.23253/) (2025)
- [MQENet: A Mesh Quality Evaluation Neural Network Based on Dynamic Graph Attention](https://mlsanity.com/paper/2309.01067/) (2023)
- [SEA++: Multi-Graph-based High-Order Sensor Alignment for Multivariate Time-Series Unsupervised Domain Adaptation](https://mlsanity.com/paper/2311.10806/) (2023)
- [Graph Decipher: A transparent dual-attention graph neural network to understand the message-passing mechanism for the node classification](https://mlsanity.com/paper/2201.01381/) (2022)
- [Beyond the Gates of Euclidean Space: Temporal-Discrimination-Fusions and Attention-based Graph Neural Network for Human Activity Recognition](https://mlsanity.com/paper/2206.04855/) (2022)
- [Fre-CW: Targeted Attack on Time Series Forecasting using Frequency Domain Loss](https://mlsanity.com/paper/2508.08955/) (2025)
- [GeoCert: Certified Geometric AI for Reliable Forecasting](https://mlsanity.com/paper/2604.23474/) (2026)

## Abstract (arXiv)

We consider a setting where multiple entities inter-act with each other over time and the time-varying statuses of the entities are represented as multiple correlated time series. For example, speed sensors are deployed in different locations in a road network, where the speed of a specific location across time is captured by the corresponding sensor as a time series, resulting in multiple speed time series from different locations, which are often correlated. To enable accurate forecasting on correlated time series, we proposes graph attention recurrent neural networks.First, we build a graph among different entities by taking into account spatial proximity and employ a multi-head attention mechanism to derive adaptive weight matrices for the graph to capture the correlations among vertices (e.g., speeds at different locations) at different timestamps. Second, we employ recurrent neural networks to take into account temporal dependency while taking into account the adaptive weight matrices learned from the first step to consider the correlations among time series.Experiments on a large real-world speed time series data set suggest that the proposed method is effective and outperforms the state-of-the-art in most settings. This manuscript provides a full version of a workshop paper [1].