Smart City Gnosys

Smart city article details

Title	Roi-Demand Traffic Prediction: A Pre-Train, Query And Fine-Tune Framework
ID_Doc	46971
Authors	Cui Y.; Li S.; Deng W.; Zhang Z.; Zhao J.; Zheng K.; Zhou X.
Year	2023
Published	Proceedings - International Conference on Data Engineering, 2023-April
DOI	http://dx.doi.org/10.1109/ICDE55515.2023.00107
Abstract	Traffic prediction has drawn increasing attention due to its essential role in smart city applications. To achieve precise predictions, a large number of approaches have been proposed to model spatial dependencies and temporal dynamics. Despite their superior performance, most existing studies focus datasets that are usually in large geographic scales, e.g., citywide, while ignoring the results on specific regions. However, in many scenarios, for example, route planning on time-dependent road networks, only small regions are of interest. We name the task of answering forecasting requests from any query region of interest (ROI) as ROI-demand traffic prediction (RTP). In this paper, we make a primary observation that existing methods fail to jointly achieve effectiveness and efficiency for RTP. To address this issue, a novel model-agnostic framework based on pre-Training, Querying and fine-Tuning, named TQT, is proposed, which first customizes input data given an ROI, and then makes fast adaptation from pre-trained traffic prediction backbone models by fine-tuning. We evaluate TQT on two real-world traffic datasets, performing both flow and speed prediction tasks. Extensive experiment results demonstrate the effectiveness and efficiency of the proposed method. © 2023 IEEE.
Author Keywords	fine-tune; pre-train; time series forecasting; traffic forecasting

Similar Articles

Id	Similarity	Authors	Title	Published
18144	0.895	Liu Z.; Huang M.; Ye Z.; Wu K.	Deeprtp: A Deep Spatio-Temporal Residual Network For Regional Traffic Prediction	Proceedings - 2019 15th International Conference on Mobile Ad-Hoc and Sensor Networks, MSN 2019 (2019)
58580	0.884	Lai P.; Li C.; Wang Z.; Wang C.; Liao D.	Traffic Flow Prediction Based On Graph Prompt-Finetuning; [基于图提示微调的交通流量预测]	Jisuanji Yanjiu yu Fazhan/Computer Research and Development, 61, 8 (2024)
1395	0.882	Tripathi A.N.; Sharma B.	A Deep Review: Techniques, Findings And Limitations Of Traffic Flow Prediction Using Machine Learning	Lecture Notes in Mechanical Engineering (2023)
38390	0.88	Tian R.; Wang C.; Hu J.; Ma Z.	Multi-Scale Spatial-Temporal Aware Transformer For Traffic Prediction	Information Sciences, 648 (2023)
47493	0.879	Yang S.; Wu Q.	Sdsinet: A Spatiotemporal Dual-Scale Interaction Network For Traffic Prediction	Applied Soft Computing, 173 (2025)
8060	0.878	Shouaib M.; Metwally K.; Badran K.	An Enhanced Time-Dependent Traffic Flow Prediction In Smart Cities	Advances in Electrical and Computer Engineering, 23, 3 (2023)
23509	0.877	Ali A.; Ullah I.; Singh S.K.; Sharafian A.; Jiang W.; I. Sherazi H.; Bai X.	Energy-Efficient Resource Allocation For Urban Traffic Flow Prediction In Edge-Cloud Computing	International Journal of Intelligent Systems, 2025, 1 (2025)
52834	0.877	Dai F.; Huang P.; Mo Q.; Xu X.; Bilal M.; Song H.	St-Innet: Deep Spatio-Temporal Inception Networks For Traffic Flow Prediction In Smart Cities	IEEE Transactions on Intelligent Transportation Systems, 23, 10 (2022)
8075	0.877	Zheng G.; Chai W.K.; Katos V.	An Ensemble Model For Short-Term Traffic Prediction In Smart City Transportation System	Proceedings - IEEE Global Communications Conference, GLOBECOM (2019)
36944	0.876	Tian R.; Wang C.; Hu J.; Ma Z.	Mfstgn: A Multi-Scale Spatial-Temporal Fusion Graph Network For Traffic Prediction	Applied Intelligence, 53, 19 (2023)