METRO: A Generic Graph Neural Network Framework for Multivariate Time Series Forecasting

Summary: METRO GNN framework for multivariate time series using multiscale temporal graphs to model dynamic cross-scale correlations. Cross-scale sampling/fusion enables efficient propagation; preserves intra/interstep relations and unifies GNN-TS models. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID: 12906
Venue: VLDB
Year: 2022
Pagerank: 5.9601852e-05
Overall Rank: 6,146 | 57.84%
DOI: 10.14778/3489496.3489503

Incoming Non-self Citations Over Time

Authors

1. Yue Cui (Hong Kong University of Science and Technology; University of Electronic Science and Technology of China)
2. Kai Zheng (University of Electronic Science and Technology of China)
3. Dingshan Cui (Huawei Cloud Database Innovation Lab)
4. Jiandong Xie (Huawei Cloud Database Innovation Lab)
5. Liwei Deng (University of Electronic Science and Technology of China)
6. Feiteng Huang (Huawei Cloud Database Innovation Lab)
7. Xiaofang Zhou (Hong Kong University of Science and Technology)

BibTeX Citation

@article{cui_vldb22,
        title = {{METRO: A Generic Graph Neural Network Framework for Multivariate Time Series Forecasting}},
        author = {Cui, Yue and Zheng, Kai and Cui, Dingshan and Xie, Jiandong and Deng, Liwei and Huang, Feiteng and Zhou, Xiaofang},
        journal = {PVLDB},
        series = {{VLDB} '22},
        volume = {15},
        number = {2},
        pages = {224--236},
        doi = {10.14778/3489496.3489503},
        url = {https://doi.org/10.14778/3489496.3489503},
        year = {2022}
}

Incoming Citations (Sorted by Pagerank)

Showing 4 of 4 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
4,038	BigST: Linear Complexity Spatio-Temporal Graph Neural Network for Traffic Forecasting on Large-Scale Road Networks	2024	VLDB	6.9431109e-05
6,261	EARLY: Efficient and Reliable Graph Neural Network for Dynamic Graphs	2023	SIGMOD	5.9366952e-05
8,503	Fight Fire with Fire: Towards Robust Graph Neural Networks on Dynamic Graphs via Actively Defense	2024	VLDB	5.4132367e-05
8,915	A Multi-Scale Decomposition MLP-Mixer for Time Series Analysis	2024	VLDB	5.3483178e-05

Outgoing Citations (Sorted by Pagerank)

Showing 0 of 0 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank	Cited Paper	Year	Venue	Pagerank

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	4,424	Classical and Contemporary Approaches to Big Time Series Forecasting	2019	SIGMOD
2	4,038	BigST: Linear Complexity Spatio-Temporal Graph Neural Network for Traffic Forecasting on Large-Scale Road Networks	2024	VLDB
3	3,899	MDTP: A Multi-source Deep Traffic Prediction Framework over Spatio-Temporal Trajectory Data	2021	VLDB
4	6,443	AutoCTS+: Joint Neural Architecture and Hyperparameter Search for Correlated Time Series Forecasting	2023	SIGMOD
5	4,589	Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic Forecasting	2022	VLDB
6	13,318	Fully Automated Correlated Time Series Forecasting in Minutes	2025	VLDB
7	10,862	GraphSparseNet: a Novel Method for Large Scale Traffic Flow Prediction	2025	VLDB
8	13,320	A Memory Guided Transformer for Time Series Forecasting	2025	VLDB
9	10,911	UFGTime: Mining Intertwined Dependencies in Multivariate Time Series via an Efficient Pure Graph Approach	2025	VLDB
10	6,078	Multiple Time Series Forecasting with Dynamic Graph Modeling	2024	VLDB