Yi-Ju Lu
Skip Abstract Section
Abstract
Forecasting spatio-temporal correlated time series of sensor values is crucial in urban applications, such as air pollution alerts, biking resource management, and intelligent transportation systems. While recent advances exploit graph neural networks (GNN) to better learn spatial and temporal dependencies between sensors, they cannot model time-evolving spatio-temporal correlations (STC) between sensors and require pre-defined graphs, which are neither always available nor totally reliable, and target at only a specific type of sensor data at one time. Moreover, since the form of time-series fluctuation is varied across sensors, a model needs to learn fluctuation modulation. To tackle these issues, in this work, we propose a novel GNN-based model, Attention-adjusted Graph Spatio-Temporal Network (AGSTN). In AGSTN, multi-graph convolution with sequential learning is developed to learn time-evolving STC. Fluctuation modulation is realized by a proposed attention adjustment mechanism. Experiments on three sensor data, air quality, bike demand, and traffic flow, exhibit that AGSTN outperforms the state-of-the-art methods.
- [1] . 1999. Modern Information Retrieval. Addison-Wesley Longman.Google Scholar
Digital Library
- [2] . 2020. Adaptive graph convolutional recurrent network for traffic forecasting. In Advances in Neural Information Processing Systems. 17804–17815.Google Scholar
- [3] . 2021. Deep spatial-temporal sequence modeling for multi-step passenger demand prediction. Fut. Gener. Comput. Syst. 121 (2021), 25–34.Google ScholarCross Ref
- [4] . 2018. Exploiting spatio-temporal correlations with multiple 3D convolutional neural networks for citywide vehicle flow prediction. In Proceedings of the IEEE International Conference on Data Mining (ICDM’18). 893–898.Google ScholarCross Ref
- [5] . 2019. Traffic graph convolutional recurrent neural network: A deep learning framework for network-scale traffic learning and forecasting. IEEE Trans. Intell. Transport. Syst. (2019), 1–12.Google Scholar
- [6] . 2019. Dynamic spatial-temporal graph convolutional neural networks for traffic forecasting. In Proceedings of the 33rd AAAI Conference on Artificial Intelligence (AAAI’19). 890–897.Google ScholarDigital Library
- [7] . 2019. Spatiotemporal multi-graph convolution network for ride-hailing demand forecasting. In Proceedings of the AAAI Conference on Artificial Intelligence. 3656–3663.Google ScholarDigital Library
- [8] . 2019. Attention based spatial-temporal graph convolutional networks for traffic flow forecasting. Proceedings of the AAAI Conference on Artificial Intelligence 33 (
07 2019), 922–929. Google ScholarDigital Library - [9] . 1997. Long short-term memory. Neural Comput. 9, 8 (1997), 1735–1780.Google ScholarDigital Library
- [10] . 2015. Dissecting urban noises from heterogeneous geo-social media and sensor data. In Proceedings of the 23rd ACM International Conference on Multimedia (MM’15). 1103–1106.Google ScholarDigital Library
- [11] . 1998. The empirical mode decomposition and the hilbert spectrum for nonlinear and non-stationary time series analysis. Proc. Roy. Soc. Lond. Ser. A: Math. Phys. Eng. Sci. 454, 1971 (1998), 903–995.Google ScholarCross Ref
- [12] . 2018. Towards station-level demand prediction for effective rebalancing in bike-sharing systems. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD’18). 378–386.Google ScholarDigital Library
- [13] Thomas N. Kipf and Max Welling. 2017. Semi-supervised classification with graph convolutional networks. In International Conference on Learning Representations.Google Scholar
- [14] . 2017. Diffusion convolutional recurrent neural network: Data-driven traffic forecasting. In Proceedings of International Conference on Learning Representations (ICLR’17).Google Scholar
- [15] . 2019. Learning heterogeneous spatial-temporal representation for bike-sharing demand prediction. In Proceedings of the 33rd AAAI Conference on Artificial Intelligence (AAAI’19). 1004–1011.Google ScholarDigital Library
- [16] . 2018. GeoMAN: Multi-level attention networks for geo-sensory time series prediction. In Proceedings of the 27th International Joint Conference on Artificial Intelligence (IJCAI’18). International Joint Conferences on Artificial Intelligence Organization, 3428–3434.Google ScholarCross Ref
- [17] . 2022. A graph neural network with spatio-temporal attention for multi-sources time series data: An application to frost forecast. Sensors 22, 4 (2022).Google ScholarCross Ref
- [18] . 2016. Urban water quality prediction based on multi-task multi-view learning. In Proceedings of the 25th International Joint Conference on Artificial Intelligence (IJCAI’16). 2576–2582.Google Scholar
- [19] . 2020. AGSTN: Learning attention-adjusted graph spatio-temporal networks for short-term urban sensor value forecasting. In Proceedings of the IEEE International Conference on Data Mining (ICDM’20). 1148–1153.Google ScholarCross Ref
- [20] . 2019. AccuAir: Winning solution to air quality prediction for KDD cup 2018. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD’19). 1842–1850.Google ScholarDigital Library
- [21] . 2017. A dual-stage attention-based recurrent neural network for time series prediction. In Proceedings of the 26th International Joint Conference on Artificial Intelligence (IJCAI’17). 2627–2633.Google ScholarCross Ref
- [22] . 2021. Discrete graph structure learning for forecasting multiple time series. In International Conference on Learning Representations.Google Scholar
- [23] . 2014. Sequence to sequence learning with neural networks. In Proceedings of the 27th International Conference on Neural Information Processing Systems, Volume 2 (NIPS’14). 3104–3112.Google ScholarDigital Library
- [24] . 2019. STAR: A concise deep learning framework for citywide human mobility prediction. In Proceedings of the 20th IEEE International Conference on Mobile Data Management (MDM’19). 304–309.Google ScholarCross Ref
- [25] . 2016. Relation classification via multi-level attention CNNs. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 1298–1307.Google ScholarCross Ref
- [26] Shuo Wang, Yanran Li, Jiang Zhang, Qingye Meng, Lingwei Meng, and Fei Gao. 2020. PM2.5-GNN: A domain knowledge enhanced graph neural network for PM2.5 forecasting. In Proceedings of the 28th International Conference on Advances in Geographic Information Systems (SIGSPATIAL’20). 163–166.Google Scholar
- [27] . 2016. Short-term traffic flow forecasting with spatial-temporal correlation in a hybrid deep learning framework.
arxiv:1612.01022 . Retrieved from https://arxiv.org/abs/1612.01022Google Scholar - [28] . 2020. A comprehensive survey on graph neural networks. IEEE Trans. Neural Netw. Learn. Syst. (2020), 1–21.Google ScholarCross Ref
- [29] . 2018. Deep distributed fusion network for air quality prediction. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD’18). 965–973.Google ScholarDigital Library
- [30] . 2018. Spatio-temporal graph convolutional neural network: A deep learning framework for traffic forecasting. In Proceedings of the 27th International Joint Conference on Artificial Intelligence (IJCAI’18).Google ScholarCross Ref
- [31] . 2017. Multi-level attention networks for visual question answering. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’17). 4187–4195.Google ScholarCross Ref
- [32] . 2017. Spatiotemporal recurrent convolutional networks for traffic prediction in transportation networks. Sensors 27 (
06 2017), 1501.Google ScholarCross Ref - [33] . 2016. DNN-based prediction model for spatio-temporal data. In Proceedings of the 24th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (SIGSPACIAL’16). Article
92 .Google ScholarDigital Library - [34] . 2018. Predicting citywide crowd flows using deep spatio-temporal residual networks. Artif. Intell. 259 (2018), 147–166.Google ScholarCross Ref
- [35] . 2015. Forecasting fine-grained air quality based on big data. In Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD’15). 2267–2276.Google ScholarDigital Library
Index Terms
- Forecasting Urban Sensory Values through Learning Attention-adjusted Graph Spatio-temporal Networks
Recommendations
SST-GNN: Simplified Spatio-Temporal Traffic Forecasting Model Using Graph Neural Network
Advances in Knowledge Discovery and Data MiningAbstractTo capture spatial relationships and temporal dynamics in traffic data, spatio-temporal models for traffic forecasting have drawn significant attention in recent years. Most of the recent works employed graph neural networks(GNN) with multiple ...
Make More Connections: Urban Traffic Flow Forecasting with Spatiotemporal Adaptive Gated Graph Convolution Network
Urban traffic flow forecasting is a critical issue in intelligent transportation systems. Due to the complexity and uncertainty of urban road conditions, how to capture the dynamic spatiotemporal correlation and make accurate predictions is very ...
Neural networks for pattern-based short-term load forecasting
In this work several univariate approaches for short-term load forecasting based on neural networks are proposed and compared. They include: multilayer perceptron, radial basis function neural network, generalized regression neural network, fuzzy ...
Comments