Learning to Transfer for Traffic Forecasting via Multi-task Learning
This work addresses the practical challenge of domain adaptation in traffic forecasting, which is incremental as it builds on existing methods to improve robustness for real-world applications.
The paper tackles the problem of traffic forecasting under domain shifts in space and time, presenting a multi-task learning framework that achieves strong empirical performance, outperforming baseline domain adaptation methods while remaining efficient.
Deep neural networks have demonstrated superior performance in short-term traffic forecasting. However, most existing traffic forecasting systems assume that the training and testing data are drawn from the same underlying distribution, which limits their practical applicability. The NeurIPS 2021 Traffic4cast challenge is the first of its kind dedicated to benchmarking the robustness of traffic forecasting models towards domain shifts in space and time. This technical report describes our solution to this challenge. In particular, we present a multi-task learning framework for temporal and spatio-temporal domain adaptation of traffic forecasting models. Experimental results demonstrate that our multi-task learning approach achieves strong empirical performance, outperforming a number of baseline domain adaptation methods, while remaining highly efficient. The source code for this technical report is available at https://github.com/YichaoLu/Traffic4cast2021.