Transfer learning with a spatiotemporal graph convolution network for city flow prediction
Regular Papers|Updated:2025-03-13
|
Transfer learning with a spatiotemporal graph convolution network for city flow prediction
Enhanced Publication
基于时空图卷积的城市流迁移预测
“In the field of smart city construction, a transfer learning method based on spatiotemporal graph convolution has been proposed. This method constructs a co-occurrence space between source and target domains and aligns the mapping of their data, achieving transfer learning of the source city flow prediction model on the target domain. It provides a new solution for cross-city bike flow prediction.”
Frontiers of Information Technology & Electronic EngineeringVol. 26, Issue 1, Pages: 79-92(2025)
Affiliations:
1.Department of Automation, University of Science and Technology of China, Hefei 230026, China
2.Key Laboratory of System Control and Information Processing, Ministry of Education, Shanghai 200240, China
3.Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei 230088, China
4.Institute of Advanced Technology, University of Science and Technology of China, Hefei 230088, China
Binkun LIU, Yu KANG, Yang CAO, et al. Transfer learning with a spatiotemporal graph convolution network for city flow prediction[J]. Frontiers of information technology & electronic engineering, 2025, 26(1): 79-92.
DOI:
Binkun LIU, Yu KANG, Yang CAO, et al. Transfer learning with a spatiotemporal graph convolution network for city flow prediction[J]. Frontiers of information technology & electronic engineering, 2025, 26(1): 79-92. DOI: 10.1631/FITEE.2300571.
Transfer learning with a spatiotemporal graph convolution network for city flow predictionEnhanced Publication