Learning from Multiple Cities: A Meta-Learning Approach for Spatial-Temporal Prediction

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 spatialtemporal 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.

Semi-Supervised Graph-to-Graph Translation

“…Each trip record contains the take-on and take-off places, as well as the trip-start time. We follow prior studies [36,[38][39][40] and split the city into 100 regions, and build the edges based on the taxi flow amount between each region pairs within one hour. This results in 365 * 24 graphs in total.…”

Knowledge Adaption for Demand Prediction based on Multi-task Memory Neural Network

“…Due to the insufficiency of sources and external data, some works utilized developed previously learning methods to adapt the knowledge to new tasks or domains for prediction [20,24,27]. An intercity region matching function was learned by Wang et al [20] to match two similar regions from the source domain to the target domain for crowd flow prediction.…”

“…For air quality prediction, a Flexible multi-modal transfer Learning (FLORAL) method was proposed by Wei et al [24] through learning semantically related dictionaries from the source domain and adapting it to the target domain. Yao et al [27] adopted meta-learning to take advantage of the knowledge from multiple cities to increase the stability of transfer for spatial-temporal prediction of the target city. These methods aimed at solving the data-scarce problem lacking training samples (e.g.…”

Adversarial Learning to Compare

“…Many recent studies [2,14,27,28,30,32,33] show that there is a strong correlation between customers' check-in activities and geographical distances. Thus leveraging geographical influences to improve the recommendation accuracy has been noticed by most of the current location-based recommendation work.…”