基于图多注意力网络预测模型在智慧城市的运用研究
DOI:
https://doi.org/10.52810/CJNS.2025.032关键词:
智慧城市, 图注意力模型, 时空预测摘要
在智慧城市建设中，精准的时空数据预测对资源优化配置和科学决策具有重要意义。目前，时空数据预测面临复杂空间依赖、深度模型过平滑和数据缺失等挑战。本文提出一种基于图多注意力网络（GMAT）的预测模型，集成图注意力网络（GAT）、信息保留模块（IRM）和层间注意力模块（ILAM），有效缓解深层图网络的过平滑和信息衰减问题。我们在三个典型数据集上进行实验：空气湿度、PM2.5 浓度和交通流量。结果表明，GMAT 在多个预测步长任务中均优于传统模型，尤其在 24 步长任务中，MAE 误差较基线模型降低超5%，显著提高了预测精度和稳定性。GMAT 在交通流量预测中同样表现优越，为复杂时空数据建模提供了新思路。参考文献
Benidis, K., Konstantinos, D., ... (2022). Deep learning for time series forecasting: Tutorial and literature survey. ACM Computing Surveys, 55(6), 1-36.
Han, Z., Zhao, J., Leung, H., & Ma, K. F. (2019). A review of deep learning models for time series prediction. IEEE Sensors Journal, 21(6), 7833-7848.
Wang, Y., Jing, C., Xu, S., & Li, Y. (2022). Attention based spatiotemporal graph attention networks for traffic flow forecasting. Information Sciences, 607, 869-883.
Gasparin, A., Lukovic, S., & Alippi, C. (2022). Deep learning for time series forecasting: The electric load case. CAAI Transactions on Intelligent Technology, 7(1), 1-25.
Gao, Z., Li, Z., Yu, J., & Wang, J. (2023). Global spatiotemporal graph attention network for sea surface temperature prediction. IEEE Geoscience and Remote Sensing Letters, 20, 1-5.
Jin, G. Y., Liang, Y. X., Yu, F., & Zhang, J. (2024). Spatio-temporal graph neural networks for predictive learning in urban computing: A survey. IEEE Transactions on Knowledge and Data Engineering. Advance online publication. https://doi.org/10.1109/TKDE.2023.3333824
Jin, M., Koh, H. Y., Wen, Q., & Pan, S. (2024). A survey on graph neural networks for time series: Forecasting, classification, imputation, and anomaly detection. IEEE Transactions on Pattern Analysis and Machine Intelligence.
Jiang, W., Luo, J., He, M., & Ni, L. (2023). Graph neural network for traffic forecasting: The research progress. ISPRS International Journal of Geo-Information, 12(3), 100.
Asif, N. A., Sarker, Y., Chakrabortty, R. K., & Ryan, M. J. (2021). Graph neural network: A comprehensive review on non-Euclidean space. IEEE Access, 9, 60588-60606.
Zhou, K., Huang, X., Song, Q., & Hu, X. (2022). Auto-gnn: Neural architecture search of graph neural networks. Frontiers in Big Data, 5, 1029307.
Chiang, W. L., Liu, X., Si, S., & Bengio, Y. (2019). Cluster-gcn: An efficient algorithm for training deep and large graph convolutional networks. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (pp. 257-266).
Liu, J., Ong, G. P., & Chen, X. (2020). GraphSAGE-based traffic speed forecasting for segment network with sparse data. IEEE Transactions on Intelligent Transportation Systems, 23(3), 1755-1766.
Huang, K., Li, X., Liu, F., & Wu, D. (2022). Ml-gat: A multilevel graph attention model for stock prediction. IEEE Access, 10, 86408-86422.
Liu, Y., Feng, T., Rasouli, S., & Kotey, D. (2024). ST-DAGCN: A spatiotemporal dual adaptive graph convolutional network model for traffic prediction. Neurocomputing, 601, 128175.
Liu, T., Jiang, A., Zhou, J., & Yu, Z. (2023). GraphSAGE-based dynamic spatial–temporal graph convolutional network for traffic prediction. IEEE Transactions on Intelligent Transportation Systems, 24(10), 11210-11224.
Einizade, A., Malliaros, F. D., & Giraldo, J. H. (2024). Spatiotemporal forecasting meets efficiency: Causal graph process neural networks. arXiv preprint. arXiv:2405.18879
Wu, Z., Pan, S., Long, G., & Jiang, J. (2019). Graph wavenet for deep spatial-temporal graph modeling. arXiv preprint. arXiv:1906.00121
Zhang, X. T., Liu, H., Li, Q. M., & Wu, X. M. (2019). Attributed graph clustering via adaptive graph convolution. arXiv preprint. arXiv:1906.01210
Zhou, J., & Yu, Q. (2023). DCRNN: A deep cross approach based on RNN for partial parameter sharing in multitask learning. arXiv preprint. arXiv:2310.11777
Gao, X., Hu, Y., Liu, S., & Li, P. (2023). An AGCRN algorithm for pressure prediction in an ultra-long mining face in a medium–thick coal seam in the northern Shaanxi area, China. Applied Sciences, 13(20), 11369.
Pei, Y., Huang, T., Van Ipenburg, W., & Pechenizkiy, M. (2022). ResGCN: Attention-based deep residual modeling for anomaly detection on attributed networks. Machine Learning, 111(2), 519-541.
Xu, K., Li, C., Tian, Y., & Weinberger, K. (2018). Representation learning on graphs with jumping knowledge networks. Proceedings of the 35th International Conference on Machine Learning (ICML) (pp. 5453-5462).
Wang, B., & Wang, J. (2022). ST-MGAT: Spatio-temporal multi-head graph attention network for traffic prediction. Physica A, 603, 127762.
Verma, V., Qu, M., Kawaguchi, K., & Tang, J. (2021). Graphmix: Improved training of gnns for semi-supervised learning. Proceedings of the 35th AAAI Conference on Artificial Intelligence, 35(11), 10024-10032.
Chen, D., Lin, Y., Li, W., & Li, P. (2020). Measuring and relieving the over-smoothing problem for graph neural networks from the topological view. Proceedings of the 34th AAAI Conference on Artificial Intelligence, 34(04), 3438- 3445.
Chen, J., Yang, L., Yang, Y., & Li, P. (2024). Spatio-temporal graph neural networks for missing data completion in traffic prediction. International Journal of Geographical Information Science, 1-19. Liu, J., Mao, H., Chen, Z., & Xiao, Y. (2024). Neural scaling laws on graphs. arXiv preprint. arXiv:2402.02054
Zhu, S., Zhou, L., Pan, S., & Wang, C. (2020). GSSNN: Graph smoothing splines neural networks. Proceedings of the 34th AAAI Conference on Artificial Intelligence, 34(04), 7007-7014.
Velickovic, P., Cucurull, G., Casanova, A., & Romero, A. (2017). Graph attention networks. Statistics, 1050(20), 10-48550.
Hyndman, R. J., & Athanasopoulos, G. (2021). Forecasting: Principles and practice (3rd ed.). OTexts. Chai, T., & Draxler, R. R. (2014). Root mean square error (RMSE) or mean absolute error (MAE)? Geoscientific Model Development, 7(3), 1247-1250. https://doi.org/10.5194/gmd-7-1247-2014
Armstrong, J. S., & Collopy, F. (1992). Error measures for generalizing about forecasting methods: Empirical comparisons. International Journal of Forecasting, 8(1), 69-80. https://doi.org/10.1016/0169-2070(92)90008-W
Navares, R., & Aznarte, J. L. (2019). Predicting air quality with deep learning LSTM: Towards comprehensive models. Ecological Informatics, 55, 101019.
Wang, Y., Liao, W., & Chang, Y. (2018). Gated recurrent unit network-based short-term photovoltaic forecasting. Energies, 11(9), 2163.
Vaswani, A., Shazeer, N., Parmar, N., & Uszkoreit, J. (2017). Attention is all you need. Advances in Neural Information Processing Systems, 30, 5998-6008.
Jin, X. B., Gong, W. T., Kong, J. L., Bai, Y. T., & Su, T. L. (2022). PFVAE: A planar flow-based variational auto-encoder prediction model for time series data. Mathematics, 10(4), 610.
##submission.downloads##
已出版
期次
栏目
引用本文
