Abstract
Graph Recurrent Neural Networks (GRNN) excel in time-series prediction by modeling complicated non-linear relationships among time-series. However, most GRNN models target small datasets that only have tens of time-series or hundreds of time-series. Therefore, they fail to handle large-scale datasets that have tens of thousands of time-series, which exist in many real-world scenarios. To address this scalability issue, we propose Evolving Super Graph Neural Networks (ESGNN), which target large-scale datasets and significantly boost model training. Our ESGNN models multivariate time-series based on super graphs, where each super node is associated with a set of time-series that are highly correlated with each other. To further precisely model dynamic relationships between time-series, ESGNN quickly updates super graphs on the fly by using the LSH algorithm to construct the super edges. The embeddings of super nodes are learned through end-to-end learning and are then used with each target time-series for forecasting. Experimental result shows that ESGNN outperforms previous state-of-the-art methods with a significant runtime speedup (\(3{\times }\)–\(40{\times }\) faster) and space-saving (\(5{\times }\)–\(4600{\times }\) less), while only sacrificing little or negligible prediction accuracy. An ablation study is also conducted to investigate the effectiveness of the number of super nodes and the graph update interval.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Alexandrov, A., et al.: GluonTS: probabilistic and neural time series modeling in Python. J. Mach. Learn. Res. 21(116), 1–6 (2020)
Chatfield, C.: Time-Series Forecasting. Chapman and Hall/CRC, New York (2000)
Chen, H., Eldardiry, H.: Graph time-series modeling in deep learning: a survey. ACM Trans. Knowl. Discov. Data 18, 1–35 (2023)
Chen, H., Rossi, R.A., Mahadik, K., Kim, S., Eldardiry, H.: Graph deep factors for forecasting with applications to cloud resource allocation. In: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining (2021)
Chen, X., Wang, J., Xie, K.: TrafficStream: a streaming traffic flow forecasting framework based on graph neural networks and continual learning. In: Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence (2021)
Chen, Y., Segovia, I., Gel, Y.R.: Z-GCNets: time zigzags at graph convolutional networks for time series forecasting. In: ICML (2021)
Du, B., Yuan, C., Wang, F., Tong, H.: Geometric matrix completion via Sylvester multi-graph neural network. In: Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, pp. 3860–3864 (2023)
Du, L., et al.: GBK-GNN: gated Bi-Kernel graph neural networks for modeling both homophily and heterophily. In: Proceedings of the ACM Web Conference 2022, pp. 1550–1558 (2022)
Li, J., et al.: Predicting path failure in time-evolving graphs. In: SIGKDD (2019)
Li, Y., Yu, R., Shahabi, C., Liu, Y.: Diffusion convolutional recurrent neural network: data-driven traffic forecasting. In: ICLR (2018)
Lim, B., Zohren, S.: Time-series forecasting with deep learning: a survey. Phil. Trans. R. Soc. A 379(2194), 20200209 (2021)
Lu, B., Gan, X., Jin, H., Fu, L., Zhang, H.: Spatiotemporal adaptive gated graph convolution network for urban traffic flow forecasting. In: CIKM (2020)
Oreshkin, B.N., Carpov, D., Chapados, N., Bengio, Y.: N-BEATS: neural basis expansion analysis for interpretable time series forecasting. In: ICLR (2020)
Pelleg, D., Moore, A.W., et al.: X-Means: extending K-Means with efficient estimation of the number of clusters. In: ICML, vol. 1, pp. 727–734 (2000)
Reiss, C., Wilkes, J., Hellerstein, J.L.: Google cluster-usage traces: format+ schema, pp. 1–14. Google Inc., White Paper (2011)
Salinas, D., Flunkert, V., Gasthaus, J., Januschowski, T.: DeepAR: probabilistic forecasting with autoregressive recurrent networks. Int. J. Forecast. 36, 1181–1191 (2020)
Shang, C., Chen, J., Bi, J.: Discrete graph structure learning for forecasting multiple time series. In: International Conference on Learning Representations (2020)
Tran, A., Mathews, A., Ong, C.S., Xie, L.: Radflow: a recurrent, aggregated, and decomposable model for networks of time series. In: The Web Conference (2021)
Wang, Y., Smola, A., Maddix, D., Gasthaus, J., Foster, D., Januschowski, T.: Deep factors for forecasting. In: ICML (2019)
Wen, R., Torkkola, K., Narayanaswamy, B., Madeka, D.: A multi-horizon quantile recurrent forecaster. arXiv preprint arXiv:1711.11053 (2017)
Wu, Z., Pan, S., Long, G., Jiang, J., Chang, X., Zhang, C.: Connecting the dots: multivariate time series forecasting with graph neural networks. In: KDD (2020)
Xing, Y., et al.: Learning hierarchical graph neural networks for image clustering. In: Proceedings of the IEEE International Conference on Computer Vision (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Chen, H., Rossi, R., Kim, S., Mahadik, K., Eldardiry, H. (2024). Evolving Super Graph Neural Networks for Large-Scale Time-Series Forecasting. In: Yang, DN., Xie, X., Tseng, V.S., Pei, J., Huang, JW., Lin, J.CW. (eds) Advances in Knowledge Discovery and Data Mining. PAKDD 2024. Lecture Notes in Computer Science(), vol 14650. Springer, Singapore. https://doi.org/10.1007/978-981-97-2266-2_16
Download citation
DOI: https://doi.org/10.1007/978-981-97-2266-2_16
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-97-2265-5
Online ISBN: 978-981-97-2266-2
eBook Packages: Computer ScienceComputer Science (R0)