Smart City Gnosys

Smart city article details

Title	Spatially Constrained Transformer With Efficient Global Relation Modelling For Spatio-Temporal Prediction
ID_Doc	52528
Authors	Sao A.; Gottschalk S.
Year	2024
Published	Frontiers in Artificial Intelligence and Applications, 392
DOI	http://dx.doi.org/10.3233/FAIA240813
Abstract	Accurate spatio-temporal prediction is crucial for the sustainable development of smart cities. However, current approaches often struggle to capture important spatio-temporal relationships, particularly overlooking global relations among distant city regions. Most existing techniques predominantly rely on Convolutional Neural Networks (CNNs) to capture global relations. However, CNNs exhibit neighbourhood bias, making them insufficient for capturing distant relations. To address this limitation, we propose ST-SAMPLENET, a novel transformer-based architecture that combines CNNs with self-attention mechanisms to capture both local and global relations effectively. Moreover, as the number of regions increases, the quadratic complexity of self-attention becomes a challenge. To tackle this issue, we introduce a lightweight region sampling strategy that prunes non-essential regions and enhances the efficiency of our approach. Furthermore, we introduce a spatially constrained position embedding that incorporates spatial neighbourhood information into the self-attention mechanism, aiding in semantic interpretation and improving the performance of ST-SAMPLENET. Our experimental evaluation on three real-world datasets demonstrates the effectiveness of ST-SAMPLENET. Additionally, our efficient variant achieves a 40% reduction in computational costs with only a marginal compromise in performance, approximately 1%. © 2024 The Authors.
Author Keywords

Similar Articles

Id	Similarity	Authors	Title	Published
52833	0.878	Zhao L.; Gao M.; Wang Z.	St-Gsp: Spatial-Temporal Global Semantic Representation Learning For Urban Flow Prediction	WSDM 2022 - Proceedings of the 15th ACM International Conference on Web Search and Data Mining (2022)
23809	0.877	Ouyang X.; Li Y.; Guo D.; Huang W.; Yang X.; Yang Y.; Zhang J.; Li T.	Enhancing Few-Sample Spatio-Temporal Prediction Via Relational Fusion-Based Hypergraph Neural Network	Information Fusion, 121 (2025)
37180	0.868	Liang Y.; Ouyang K.; Wang Y.; Pan Z.; Yin Y.; Chen H.; Zhang J.; Zheng Y.; Rosenblum D.S.; Zimmermann R.	Mixed-Order Relation-Aware Recurrent Neural Networks For Spatio-Temporal Forecasting	IEEE Transactions on Knowledge and Data Engineering, 35, 9 (2023)
53042	0.865	Jin Z.; Xu J.; Huang R.; Shao W.; Xiao X.	Stm2Cn: A Multi-Graph Attention-Based Framework For Sensor Data Prediction In Smart Cities	Proceedings of the International Joint Conference on Neural Networks, 2022-July (2022)
26541	0.865	Liang Y.; Ouyang K.; Sun J.; Wang Y.; Zhang J.; Zheng Y.; Rosenblum D.; Zimmermann R.	Fine-Grained Urban Flow Prediction	The Web Conference 2021 - Proceedings of the World Wide Web Conference, WWW 2021 (2021)
59338	0.865	Fang J.; Chen L.; Chai D.; Hong Y.; Xie X.; Chen L.; Wang L.	Uctb: An Urban Computing Tool Box For All-In-One Spatiotemporal Prediction Solution	CCF Transactions on Pervasive Computing and Interaction (2025)
19926	0.864	Yin X.; Wu L.; Zhang Y.; Han Y.; Zhai K.	Diffusion Convolution Graph Attention Network For Spatial-Temporal Prediction	Lecture Notes in Electrical Engineering, 996 LNEE (2023)
59339	0.863	Fang J.; Chen L.; Chai D.; Hong Y.; Xie X.; Chen L.; Wang L.	Uctb: An Urban Computing Tool Box For Building Spatiotemporal Prediction Services	Proceedings - 2024 IEEE International Conference on Software Services Engineering, SSE 2024 (2024)
52516	0.863	Dao M.-S.; Zetsu K.; Hoang D.-T.	Spatial-Temporal Graph Transformer Network For Spatial-Temporal Forecasting	Proceedings - 2024 IEEE International Conference on Big Data, BigData 2024 (2024)
52830	0.862	Yang J.	St-Cnn+Transformer: A Novel Approach For Data Fusion And Urban Functional Zone Recognition	Proceedings of 2025 3rd International Conference on Communication Networks and Machine Learning, CNML 2025 (2025)