Spatio-Temporal Knowledge Transfer for Urban Crowd Flow Prediction via Deep Attentive Adaptation Networks | IEEE Journals & Magazine | IEEE Xplore

Spatio-Temporal Knowledge Transfer for Urban Crowd Flow Prediction via Deep Attentive Adaptation Networks


Abstract:

Accurately predicting the urban spatio-temporal data is critically important to various urban computing tasks for smart city related applications such as crowd flow predi...Show More

Abstract:

Accurately predicting the urban spatio-temporal data is critically important to various urban computing tasks for smart city related applications such as crowd flow prediction and traffic congestion prediction. Existing models especially deep learning based approaches require a large volume of training data, whose performance may degrade remarkably when the data is scarce. Recent works try to transfer knowledge from the intra-city or cross-city multi-modal spatio-temporal data. However, the careful design of what to transfer and how between the multi-modal spatio-temporal data needs to be determined in advance. There still lacks an end-to-end solution that can automatically capture the common cross-domain knowledge. In this paper, we propose a Deep Attentive Adaptation Network model named ST-DAAN to transfer cross-domain Spatio-Temporal knowledge for urban crowd flow prediction. ST-DAAN first maps the raw spatio-temporal data of source domain and target domain to a common embedding space. Then domain adaptation is adopted on several domain-specific layers through adding a domain discrepancy penalty to explicitly match the mean embeddings of the two domain distributions. Considering the complex spatial correlation in many urban spatio-temporal data, a global attention mechanism is also designed to enable the model to capture broader spatial dependencies. Using urban crowd flow prediction as a demonstration, we conduct experiments on five real-world large datasets over both intra- and cross-city transfer learning. The results demonstrate that ST-DAAN outperforms state-of-the-art methods by a large margin.
Page(s): 4695 - 4705
Date of Publication: 10 February 2021

ISSN Information:

Funding Agency:

Author image of Senzhang Wang
School of Computer Science and Engineering, Central South University, Changsha, China
Senzhang Wang (Member, IEEE) received the B.Sc. degree from Southeast University, Nanjing, China, in 2009, and the Ph.D. degree from Beihang University, Beijing, China, in 2016. He is currently a Professor with the School of Computer Science and Engineering, Central South University. His main research focus is on spatiotemporal data mining, graph data mining, and urban computing. He has published more than 90 referred con...Show More
Senzhang Wang (Member, IEEE) received the B.Sc. degree from Southeast University, Nanjing, China, in 2009, and the Ph.D. degree from Beihang University, Beijing, China, in 2016. He is currently a Professor with the School of Computer Science and Engineering, Central South University. His main research focus is on spatiotemporal data mining, graph data mining, and urban computing. He has published more than 90 referred con...View more
Author image of Hao Miao
College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China
Hao Miao received the B.S. degree in computer science and technology from Nanjing Tech University, Nanjing, China, in 2018. He is currently pursuing the master’s degree with the Department of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics. From September 2019 to November 2019, he was a Visiting Student with Hong Kong Polytechnic University, Hong Kong. His research interests include spa...Show More
Hao Miao received the B.S. degree in computer science and technology from Nanjing Tech University, Nanjing, China, in 2018. He is currently pursuing the master’s degree with the Department of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics. From September 2019 to November 2019, he was a Visiting Student with Hong Kong Polytechnic University, Hong Kong. His research interests include spa...View more
Author image of Jiyue Li
College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China
Jiyue Li received the B.S. degree in software engineering from Guangzhou University, Guangzhou, China, in 2020. She is currently pursuing the master’s degree with the Department of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics. In July 2019, she was a Visiting Student with the University of Washington, Seattle, USA. Her research interests include spatiotemporal data mining and deep le...Show More
Jiyue Li received the B.S. degree in software engineering from Guangzhou University, Guangzhou, China, in 2020. She is currently pursuing the master’s degree with the Department of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics. In July 2019, she was a Visiting Student with the University of Washington, Seattle, USA. Her research interests include spatiotemporal data mining and deep le...View more
Author image of Jiannong Cao
Department of Computing, The Hong Kong Polytechnic University, Hong Kong
Jiannong Cao (Fellow, IEEE) received the B.Sc. degree in computer science from Nanjing University, China, in 1982, and the M.Sc. and Ph.D. degrees in computer science from Washington State University, USA, in 1986 and 1990 respectively. He is currently a Chair Professor with the Department of Computing, The Hong Kong Polytechnic University, Hong Kong. His research interests include parallel and distributed computing, wire...Show More
Jiannong Cao (Fellow, IEEE) received the B.Sc. degree in computer science from Nanjing University, China, in 1982, and the M.Sc. and Ph.D. degrees in computer science from Washington State University, USA, in 1986 and 1990 respectively. He is currently a Chair Professor with the Department of Computing, The Hong Kong Polytechnic University, Hong Kong. His research interests include parallel and distributed computing, wire...View more

Author image of Senzhang Wang
School of Computer Science and Engineering, Central South University, Changsha, China
Senzhang Wang (Member, IEEE) received the B.Sc. degree from Southeast University, Nanjing, China, in 2009, and the Ph.D. degree from Beihang University, Beijing, China, in 2016. He is currently a Professor with the School of Computer Science and Engineering, Central South University. His main research focus is on spatiotemporal data mining, graph data mining, and urban computing. He has published more than 90 referred conference and journal papers.
Senzhang Wang (Member, IEEE) received the B.Sc. degree from Southeast University, Nanjing, China, in 2009, and the Ph.D. degree from Beihang University, Beijing, China, in 2016. He is currently a Professor with the School of Computer Science and Engineering, Central South University. His main research focus is on spatiotemporal data mining, graph data mining, and urban computing. He has published more than 90 referred conference and journal papers.View more
Author image of Hao Miao
College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China
Hao Miao received the B.S. degree in computer science and technology from Nanjing Tech University, Nanjing, China, in 2018. He is currently pursuing the master’s degree with the Department of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics. From September 2019 to November 2019, he was a Visiting Student with Hong Kong Polytechnic University, Hong Kong. His research interests include spatiotemporal data mining, deep learning, and transfer learning.
Hao Miao received the B.S. degree in computer science and technology from Nanjing Tech University, Nanjing, China, in 2018. He is currently pursuing the master’s degree with the Department of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics. From September 2019 to November 2019, he was a Visiting Student with Hong Kong Polytechnic University, Hong Kong. His research interests include spatiotemporal data mining, deep learning, and transfer learning.View more
Author image of Jiyue Li
College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China
Jiyue Li received the B.S. degree in software engineering from Guangzhou University, Guangzhou, China, in 2020. She is currently pursuing the master’s degree with the Department of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics. In July 2019, she was a Visiting Student with the University of Washington, Seattle, USA. Her research interests include spatiotemporal data mining and deep learning.
Jiyue Li received the B.S. degree in software engineering from Guangzhou University, Guangzhou, China, in 2020. She is currently pursuing the master’s degree with the Department of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics. In July 2019, she was a Visiting Student with the University of Washington, Seattle, USA. Her research interests include spatiotemporal data mining and deep learning.View more
Author image of Jiannong Cao
Department of Computing, The Hong Kong Polytechnic University, Hong Kong
Jiannong Cao (Fellow, IEEE) received the B.Sc. degree in computer science from Nanjing University, China, in 1982, and the M.Sc. and Ph.D. degrees in computer science from Washington State University, USA, in 1986 and 1990 respectively. He is currently a Chair Professor with the Department of Computing, The Hong Kong Polytechnic University, Hong Kong. His research interests include parallel and distributed computing, wire-less networks and mobile computing, big data and cloud computing, pervasive computing, and fault tolerant computing. He has coauthored five books in mobile computing and wireless sensor networks, co-edited none books, and published over 500 papers in major international journals and conference proceedings. He is a Distinguished Member of ACM and a Senior Member of China Computer Federation (CCF).
Jiannong Cao (Fellow, IEEE) received the B.Sc. degree in computer science from Nanjing University, China, in 1982, and the M.Sc. and Ph.D. degrees in computer science from Washington State University, USA, in 1986 and 1990 respectively. He is currently a Chair Professor with the Department of Computing, The Hong Kong Polytechnic University, Hong Kong. His research interests include parallel and distributed computing, wire-less networks and mobile computing, big data and cloud computing, pervasive computing, and fault tolerant computing. He has coauthored five books in mobile computing and wireless sensor networks, co-edited none books, and published over 500 papers in major international journals and conference proceedings. He is a Distinguished Member of ACM and a Senior Member of China Computer Federation (CCF).View more

Contact IEEE to Subscribe

References

References is not available for this document.