Cross-City Transfer Learning for Deep Spatio-Temporal Prediction
This addresses data scarcity in urban computing for cities with limited data, but it is incremental as it builds on existing transfer learning approaches.
The paper tackles the problem of data scarcity in spatio-temporal prediction for cities by proposing a cross-city transfer learning method called RegionTrans, which reduces prediction error by up to 10.7% compared to state-of-the-art fine-tuning models in crowd flow prediction.
Spatio-temporal prediction is a key type of tasks in urban computing, e.g., traffic flow and air quality. Adequate data is usually a prerequisite, especially when deep learning is adopted. However, the development levels of different cities are unbalanced, and still many cities suffer from data scarcity. To address the problem, we propose a novel cross-city transfer learning method for deep spatio-temporal prediction tasks, called RegionTrans. RegionTrans aims to effectively transfer knowledge from a data-rich source city to a data-scarce target city. More specifically, we first learn an inter-city region matching function to match each target city region to a similar source city region. A neural network is designed to effectively extract region-level representation for spatio-temporal prediction. Finally, an optimization algorithm is proposed to transfer learned features from the source city to the target city with the region matching function. Using citywide crowd flow prediction as a demonstration experiment, we verify the effectiveness of RegionTrans. Results show that RegionTrans can outperform the state-of-the-art fine-tuning deep spatio-temporal prediction models by reducing up to 10.7% prediction error.