Transfer learning with a spatiotemporal graph convolution network for city flow prediction

Recently, deep learning based city flow prediction has been extensively used in the establishment of smart cities. These methods are data-hungry, making them unscalable to areas lacking data. Although transfer learning can use data-rich source domains to assist target domain cities in city flow prediction, the performance of existing methods cannot meet the needs of actual use, because the long-distance road network connectivity is ignored. To solve this problem, we propose a transfer learning method based on spatiotemporal graph convolution, in which we construct a co-occurrence space between the source and target domains, and then align the mapping of the source and target domains’ data in this space, to achieve the transfer learning of the source city flow prediction model on the target domain. Specifically, a dynamic spatiotemporal graph convolution module along with a temporal encoder is devised to simultaneously capture the concurrent spatiotemporal features, which implies the inherent relationship among the road network structures, human travel habits, and city bike flow. Then, these concurrent features are leveraged as cross-city invariant representations and nonlinearly spanned to a co-occurrence space. The target domain features are thereby aligned with the source domain features in the co-occurrence space by using a Mahalanobis distance loss, to achieve cross-city bike flow prediction. The proposed method is evaluated on the public bike flow datasets in Chicago, New York, and Washington in 2015, and significantly outperforms state-of-the-art techniques.