Pre-training Enhanced Spatial-temporal Graph Neural Network for Multivariate Time Series Forecasting
Open accessThe DOI matches its Crossref record; 38 of the 38 references it cites were found in a registry or an index.
Abstract
Multivariate Time Series (MTS) forecasting plays a vital role in a wide range of applications. Recently, Spatial-Temporal Graph Neural Networks (STGNNs) have become increasingly popular MTS forecasting methods. STGNNs jointly model the spatial and temporal patterns of MTS through graph neural networks and sequential models, significantly improving the prediction accuracy. But limited by model complexity, most STGNNs only consider short-term historical MTS data, such as data over the past one hour. However, the patterns of time series and the dependencies between them (i.e., the temporal and spatial patterns) need to be analyzed based on long-term historical MTS data. To address this issue, we propose a novel framework, in which STGNN is Enhanced by a scalable time series Pre-training model (STEP). Specifically, we design a pre-training model to efficiently learn temporal patterns from very long-term history time series (e.g., the past two weeks) and generate segment-level representations. These representations provide contextual information for short-term time series input to STGNNs and facilitate modeling dependencies between time series. Experiments on three public real-world datasets demonstrate that our framework is capable of significantly enhancing downstream STGNNs, and our pre-training model aptly captures temporal patterns.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Exploiting Generative AI to Scale up Intelligent Tutoring Systems
Jakubův, J., Chvalovský, K., Goertzel, Z., Kaliszyk, C., Olšák, M., Piotrowski, B., Schulz, S., Suda, M., & Urban, J. (2023) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.itp.2023.19 · Cited by 76,658
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al. (2020) · arXiv · doi:10.48550/arxiv.2010.11929 · Cited by 47,472
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372 · cited 5×
“Prominent examples are the BERT [8] and GPT [3], which are based on the Transformer encoder and decoder, respec-”
BackgroundMethodInfluentialSequence to Sequence Learning with Neural Networks
Sutskever, I., Vinyals, O., & Le, Q. V. (2014) · arXiv · doi:10.48550/arxiv.1409.3215 · Cited by 17,766
Kaugeranna, R., Kaugeranna, E., & Aion, (. S. 4. 6. (2023) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.giscience.2023.43 · Cited by 13,690
A tutorial on support vector regression
Smola, A. J., & Schölkopf, B. (2004) · Statistics and Computing · doi:10.1023/b:stco.0000035301.49549.88 · Cited by 13,387
Decoupled Weight Decay Regularization
Loshchilov, I., & Hutter, F. (2017) · arXiv · doi:10.48550/arxiv.1711.05101 · Cited by 12,522
Deep Contextualized Word Representations
Peters, M., Neumann, M., Iyyer, M., Gardner, M., Clark, C., Lee, K., & Zettlemoyer, L. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) · doi:10.18653/v1/n18-1202 · Cited by 11,983
Masked Autoencoders Are Scalable Vision Learners
He, K., Chen, X., Xie, S., Li, Y., Dollar, P., & Girshick, R. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01553 · Cited by 8,489
On the Properties of Neural Machine Translation: Encoder–Decoder Approaches
Cho, K., van Merrienboer, B., Bahdanau, D., & Bengio, Y. (2014) · Proceedings of SSST-8, Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation · doi:10.3115/v1/w14-4012 · Cited by 7,099
Advances In Deep Learning On Graphs (Gsp'18 Workshop)
Defferrard, M. (2016) · Figshare · doi:10.5281/zenodo.1286817 · Cited by 4,613
Categorical Reparameterization with Gumbel-Softmax
Jang, E., Gu, S., & Poole, B. (2016) · arXiv · doi:10.48550/arxiv.1611.01144 · Cited by 3,616
T-GCN: A Temporal Graph Convolutional Network for Traffic Prediction
Zhao, L., Song, Y., Zhang, C., Liu, Y., Wang, P., Lin, T., Deng, M., & Li, H. (2020) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2019.2935152 · Cited by 3,326
Attention Based Spatial-Temporal Graph Convolutional Networks for Traffic Flow Forecasting
Guo, S., Lin, Y., Feng, N., Song, C., & Wan, H. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.3301922 · Cited by 3,123 · cited 4×
“Moreover, attention mechanism is widely used in many methods, such as GMAN [41] and ASTGCN [11].”
BackgroundMethodInfluentialGraph WaveNet for Deep Spatial-Temporal Graph Modeling
Wu, Z., Pan, S., Long, G., Jiang, J., & Zhang, C. (2019) · Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2019/264 · Cited by 2,948
Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks
Wu, Z., Pan, S., Long, G., Jiang, J., Chang, X., & Zhang, C. (2020) · Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining · doi:10.1145/3394486.3403118 · Cited by 2,001
GMAN: A Graph Multi-Attention Network for Traffic Prediction
Zheng, C., Fan, X., Wang, C., & Qi, J. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i01.5477 · Cited by 1,730
Artificial intelligence: A powerful paradigm for scientific research
Xu, Y., Liu, X., Cao, X., Huang, C., Liu, E., Qian, S., Liu, X., Wu, Y., Dong, F., Qiu, C.-W., et al. (2021) · The Innovation · doi:10.1016/j.xinn.2021.100179 · Cited by 1,726 · cited 1×
“The accuracy ofmultivariate time series forecasting has been largely improved by artificial intelligence [37], especially deep learning techniques.”
BackgroundSelf-citationPre-trained models for natural language processing: A survey
Qiu, X., Sun, T., Xu, Y., Shao, Y., Dai, N., & Huang, X. (2020) · Science China Technological Sciences · doi:10.1007/s11431-020-1647-3 · Cited by 1,591 · cited 1×
“Recent studies have demonstrated significant performance gains on many natural language processing tasks with the help of the representation extracted from pre-training models [28].”
BackgroundSelf-citationSong, C., Lin, Y., Guo, S., & Wan, H. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i01.5438 · Cited by 1,574
The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
Maddison, C. J., Mnih, A., & Teh, Y. W. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.00712 · Cited by 1,359
A Transformer-based Framework for Multivariate Time Series Representation Learning
Zerveas, G., Jayaraman, S., Patel, D., Bhamidipaty, A., & Eickhoff, C. (2021) · Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining · doi:10.1145/3447548.3467401 · Cited by 1,278
Big data and its technical challenges.
Jagadish, H. V., Gehrke, J., Labrinidis, A., Papakonstantinou, Y., Patel, J. M., Ramakrishnan, R., & Shahabi, C. (2014) · Communications of the ACM · doi:10.1145/2611567 · Cited by 1,048 · cited 1×
“• METR-LA is a traffic speed dataset collected from loopdetectors located on the LA County road network [14].”
BackgroundNew Introduction to Multiple Time Series Analysis
(2005) · Springer eBooks · doi:10.1007/3-540-27752-8 · Cited by 831
Learning Dynamics and Heterogeneity of Spatial-Temporal Graph Data for Traffic Forecasting
Guo, S., Lin, Y., Wan, H., Li, X., & Cong, G. (2022) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2021.3056502 · Cited by 764
Freeway Performance Measurement System: Mining Loop Detector Data
Chen, C., Petty, K., Skabardonis, A., Varaiya, P., & Jia, Z. (2001) · Transportation Research Record: Journal of the Transportation Research Board · doi:10.3141/1748-12 · Cited by 746
Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting
Bai, L., Yao, L., Li, C., Wang, X., & Wang, C. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.02842 · Cited by 701
Traffic Flow Prediction via Spatial Temporal Graph Neural Network
Wang, X., Ma, Y., Wang, Y., Jin, W., Wang, X., Tang, J., Jia, C., & Yu, J. (2020) · Proceedings of The Web Conference 2020 · doi:10.1145/3366423.3380186 · Cited by 644
Urban Traffic Prediction from Spatio-Temporal Data Using Deep Meta Learning
Pan, Z., Liang, Y., Wang, W., Yu, Y., Zheng, Y., & Zhang, J. (2019) · Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining · doi:10.1145/3292500.3330884 · Cited by 559
Dynamic Graph Convolutional Recurrent Network for Traffic Prediction: Benchmark and Solution
Li, F., Feng, J., Yan, H., Jin, G., Yang, F., Sun, F., Jin, D., & Li, Y. (2023) · ACM Transactions on Knowledge Discovery from Data · doi:10.1145/3532611 · Cited by 555
Neural Relational Inference for Interacting Systems
Kipf, T., Fetaya, E., Wang, K.-C., Welling, M., & Zemel, R. S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1802.04687 · Cited by 235
Learning Discrete Structures for Graph Neural Networks
Franceschi, L., Niepert, M., Pontil, M., & He, X. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.11960 · Cited by 167
Integrating Granger Causality and Vector Auto-Regression for Traffic Prediction of Large-Scale WLANs
Lu, Z. Y., Zhou, C., Wu, J., Jiang, H., & Cui, S. (2016) · KSII Transactions on Internet and Information Systems · doi:10.3837/tiis.2016.01.008 · Cited by 127
Discrete Graph Structure Learning for Forecasting Multiple Time Series
Shang, C., Chen, J., & Bi, J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.06861 · Cited by 93
REST: Reciprocal Framework for Spatiotemporal-coupled Predictions
Lin, H., Fan, Y., Zhang, J., & Bai, B. (2021) · International World Wide Web Conference (WWW) · doi:10.1145/3442381.3449928 · Cited by 14
Chen, T., Wang, Z., Li, L., Li, D., Li, Z., Chang, X., Bian, P., Liang, G., Wang, Q., & Xie, T. (2025) · Schloss Dagstuhl – Leibniz-Zentrum für Informatik · doi:10.4230/lipics.ecoop.2025.6
Research works printed but not linked: 8
- Sami Abu-El-Haija, Bryan Perozzi, Amol Kapoor, Nazanin Alipourfard, Kristina Lerman, Hrayr Harutyunyan, Greg Ver Steeg, and Aram Galstyan. 2019. MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing. In ICML.
- Defu Cao Yujing Wang Juanyong Duan Ce Zhang Xia Zhu Congrui Huang Yunhai Tong Bixiong Xu Jing Bai Jie Tong and Qi Zhang. 2020. Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting. In NeurIPS.
- Michaël Defferrard Xavier Bresson and Pierre Vandergheynst. 2016. Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering. In NeurIPS.
- Thomas N. Kipf and Max Welling. 2017. Semi-Supervised Classification with Graph Convolutional Networks. In ICLR.
- Yaguang Li Rose Yu Cyrus Shahabi and Yan Liu. 2018. Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting. In ICLR.
- Ilya Loshchilov and Frank Hutter. 2018. DecoupledWeight Decay Regularization. In ICLR.
- Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N. Gomez Lukasz Kaiser and Illia Polosukhin. 2017. Attention is All you Need. In NeurIPS.
- Bing Yu Haoteng Yin and Zhanxing Zhu. 2018. Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting. In IJCAI.
Cited by
Spatio-Temporal Graph Neural Networks for Predictive Learning in Urban Computing: A Survey
Jin, G., Liang, Y., Fang, Y., Shao, Z., Huang, J., Zhang, J., & Zheng, Y. (2024) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2023.3333824 · Cited by 568
Self-citationJin, M., Koh, H. Y., Wen, Q., Zambon, D., Alippi, C., Webb, G. I., King, I., & Pan, S. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3443141 · Cited by 567
Spatio-Temporal Adaptive Embedding Makes Vanilla Transformer SOTA for Traffic Forecasting
Liu, H., Dong, Z., Jiang, R., Deng, J., Deng, J., Chen, Q., & Song, X. (2023) · Proceedings of the 32nd ACM International Conference on Information and Knowledge Management · doi:10.1145/3583780.3615160 · Cited by 383
Spatio-Temporal Meta-Graph Learning for Traffic Forecasting
Jiang, R., Wang, Z., Yong, J., Jeph, P., Chen, Q., Kobayashi, Y., Song, X., Fukushima, S., & Suzumura, T. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i7.25976 · Cited by 313
Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospects
Zhang, K., Wen, Q., Zhang, C., Cai, R., Jin, M., Liu, Y., Zhang, J. Y., Liang, Y., Pang, G., Song, D., et al. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3387317 · Cited by 295
“STEP[74]dividedthe seriesintomultiplenon-overlappingsegmentsofequallength andthenrandomlyselectedacertainproportionofthesegments formasking.”
Metadata
- Authors
- Shao, Z., Zhang, Z., Wang, F., & Xu, Y.
- Affiliations
- Chinese Academy of Sciences (CN)
- ORCID
- Xu, Yongjun
- Venue
- Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
- Publisher
- ACM
- Published
- 2022-08-14
- Pages
- 1567-1577
- OpenAlex
- W4283315029
- Cited by
- 338
- References
- 38
- Citations by year
- 2026: 68 · 2025: 119 · 2024: 108 · 2023: 41 · 2022: 2
- FWCI
- 148.43
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University) (cc-by)
- Funders
- China Postdoctoral Science Foundation (No. 2021M703273)
- National Science Foundation of China (No. 61902376 and 61902382)
- Topics
- Social Sciences › Transportation › Traffic Prediction and Management Techniques
- Physical Sciences › Computer Science › Signal Processing › Time Series Analysis and Forecasting
- Physical Sciences › Computer Science › Artificial Intelligence › Advanced Graph Neural Networks
- Keywords
- multivariate time series forecasting, spatio-temporal graph neural networks, pre-training, temporal pattern learning, contextual information, spatiotemporal dependencies
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.