Leveraging Multiple Source Cities in Selective Transfer Learning for Traffic Prediction With Limited Data

Traffic prediction with limited data becomes increasingly momentous and attracts a lot of attention because the urban data scarcity problem is common and often leads to low prediction precision in the practical application. Cross-city transfer learning based on deep learning can effectively alleviate the above problem by transferring knowledge data-rich source cities to data-poor target cities. Recently, a selectively cross-city method is proposed and achieves state-of-the-art precision. Nonetheless, its knowledge transfer is only suitable for utilizing one source city. The diversity of knowledge from just one source city is usually inadequate for effective transferring. To address this problem, this paper proposes <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">C</b>ross-<bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">M</b>ultiple-<bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">S</b>ource-cities selective transfer learning via <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">V</b>irtual <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">C</b>ity (CMSVC) for traffic prediction with limited data that can effectively exploit knowledge of multiple source cities. We propose a novel virtual city mechanism to integrate beneficial regions for the target city from multiple source cities. To implement this mechanism, we compare the time-series and geographic information of the source and target cities by adopting appropriate similarity metrics. Additionally, we adopt the depth-first search algorithm to extract areas so as to maintain the geographical adjacency relationship. After the virtual city mechanism, these beneficial regions are fused and can be the input for the graph neural network and meta-learning mechanism to obtain weights for selective learning. We evaluate our method on four traffic real-world datasets. The extensive experimental results demonstrate that CMSVC outperforms the state-of-the-art method. The source code of CMSVC is available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/pku-smart-city/source_code/tree/main/CMSVC</uri>