Abstract
Spatial-temporal prediction is a fundamental problem for constructing smart city, which is useful for tasks such as traffic control, taxi dispatching, and environment policy making. Due to data collection mechanism, it is common to see data collection with unbalanced spatial distributions. For example, some cities may release taxi data for multiple years while others only release a few days of data; some regions may have constant water quality data monitored by sensors whereas some regions only have a small collection of water samples. In this paper, we tackle the problem of spatial-temporal prediction for the cities with only a short period of data collection. We aim to utilize the long-period data from other cities via transfer learning. Different from previous studies that transfer knowledge from one single source city to a target city, we are the first to leverage information from multiple cities to increase the stability of transfer. Specifically, our proposed model is designed as a spatial-temporal network with a meta-learning paradigm. The meta-learning paradigm learns a well-generalized initialization of the spatial-temporal network, which can be effectively adapted to target cities. In addition, a pattern-based spatial-temporal memory is designed to distill long-term temporal information (i.e., periodicity). We conduct extensive experiments on two tasks: traffic (taxi and bike) prediction and water quality prediction. The experiments demonstrate the effectiveness of our proposed model over several competitive baseline models.
| Original language | English (US) |
|---|---|
| Title of host publication | The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019 |
| Publisher | Association for Computing Machinery, Inc |
| Pages | 2181-2191 |
| Number of pages | 11 |
| ISBN (Electronic) | 9781450366748 |
| DOIs | |
| State | Published - May 13 2019 |
| Event | 2019 World Wide Web Conference, WWW 2019 - San Francisco, United States Duration: May 13 2019 → May 17 2019 |
Publication series
| Name | The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019 |
|---|
Conference
| Conference | 2019 World Wide Web Conference, WWW 2019 |
|---|---|
| Country | United States |
| City | San Francisco |
| Period | 5/13/19 → 5/17/19 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Computer Networks and Communications
- Software
Cite this
}
Learning from multiple cities : A meta-learning approach for spatial-temporal prediction. / Yao, Huaxiu; Liu, Yiding; Wei, Ying; Tang, Xianfeng; Li, Zhenhui.
The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019. Association for Computing Machinery, Inc, 2019. p. 2181-2191 (The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
TY - GEN
T1 - Learning from multiple cities
T2 - A meta-learning approach for spatial-temporal prediction
AU - Yao, Huaxiu
AU - Liu, Yiding
AU - Wei, Ying
AU - Tang, Xianfeng
AU - Li, Zhenhui
PY - 2019/5/13
Y1 - 2019/5/13
N2 - Spatial-temporal prediction is a fundamental problem for constructing smart city, which is useful for tasks such as traffic control, taxi dispatching, and environment policy making. Due to data collection mechanism, it is common to see data collection with unbalanced spatial distributions. For example, some cities may release taxi data for multiple years while others only release a few days of data; some regions may have constant water quality data monitored by sensors whereas some regions only have a small collection of water samples. In this paper, we tackle the problem of spatial-temporal prediction for the cities with only a short period of data collection. We aim to utilize the long-period data from other cities via transfer learning. Different from previous studies that transfer knowledge from one single source city to a target city, we are the first to leverage information from multiple cities to increase the stability of transfer. Specifically, our proposed model is designed as a spatial-temporal network with a meta-learning paradigm. The meta-learning paradigm learns a well-generalized initialization of the spatial-temporal network, which can be effectively adapted to target cities. In addition, a pattern-based spatial-temporal memory is designed to distill long-term temporal information (i.e., periodicity). We conduct extensive experiments on two tasks: traffic (taxi and bike) prediction and water quality prediction. The experiments demonstrate the effectiveness of our proposed model over several competitive baseline models.
AB - Spatial-temporal prediction is a fundamental problem for constructing smart city, which is useful for tasks such as traffic control, taxi dispatching, and environment policy making. Due to data collection mechanism, it is common to see data collection with unbalanced spatial distributions. For example, some cities may release taxi data for multiple years while others only release a few days of data; some regions may have constant water quality data monitored by sensors whereas some regions only have a small collection of water samples. In this paper, we tackle the problem of spatial-temporal prediction for the cities with only a short period of data collection. We aim to utilize the long-period data from other cities via transfer learning. Different from previous studies that transfer knowledge from one single source city to a target city, we are the first to leverage information from multiple cities to increase the stability of transfer. Specifically, our proposed model is designed as a spatial-temporal network with a meta-learning paradigm. The meta-learning paradigm learns a well-generalized initialization of the spatial-temporal network, which can be effectively adapted to target cities. In addition, a pattern-based spatial-temporal memory is designed to distill long-term temporal information (i.e., periodicity). We conduct extensive experiments on two tasks: traffic (taxi and bike) prediction and water quality prediction. The experiments demonstrate the effectiveness of our proposed model over several competitive baseline models.
UR - http://www.scopus.com/inward/record.url?scp=85066891265&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85066891265&partnerID=8YFLogxK
U2 - 10.1145/3308558.3313577
DO - 10.1145/3308558.3313577
M3 - Conference contribution
AN - SCOPUS:85066891265
T3 - The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019
SP - 2181
EP - 2191
BT - The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019
PB - Association for Computing Machinery, Inc
ER -