Graph-ResNets for short-term traffic forecasts in almost unknown cities

Henry Martin, Dominik Bucher, Ye Hong, René Buffat, Christian Rupprecht, Martin Raubal
Proceedings of the NeurIPS 2019 Competition and Demonstration Track, PMLR 123:153-163, 2020.

Abstract

The 2019 IARAI traffic4cast competition is a traffic forecasting problem based on traffic data from three cities that are encoded as images. We developed a ResNet-inspired graph convolutional neural network (GCN) approach that uses street network-based subgraphs of the image lattice graphs as a prior. We train the Graph-ResNet together with GCN and convolutional neural network (CNN) benchmark models on Moscow traffic data and use them to first predict the traffic in Moscow and then to predict the traffic in Berlin and Istanbul. The results suggest that the graph-based models have superior generalization properties than CNN-based models for this application. We argue that in contrast to purely image-based approaches, formulating the prediction problem on a graph allows the neural network to learn properties given by the underlying street network. This facilitates the transfer of a learned network to predict the traffic status at unknown locations.

Cite this Paper

BibTeX
@InProceedings{pmlr-v123-martin20a, title = {Graph-ResNets for short-term traffic forecasts in almost unknown cities}, author = {Martin, Henry and Bucher, Dominik and Hong, Ye and Buffat, Ren\'e and Rupprecht, Christian and Raubal, Martin}, booktitle = {Proceedings of the NeurIPS 2019 Competition and Demonstration Track}, pages = {153--163}, year = {2020}, editor = {Escalante, Hugo Jair and Hadsell, Raia}, volume = {123}, series = {Proceedings of Machine Learning Research}, month = {08--14 Dec}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v123/martin20a/martin20a.pdf}, url = {https://proceedings.mlr.press/v123/martin20a.html}, abstract = {The 2019 IARAI traffic4cast competition is a traffic forecasting problem based on traffic data from three cities that are encoded as images. We developed a ResNet-inspired graph convolutional neural network (GCN) approach that uses street network-based subgraphs of the image lattice graphs as a prior. We train the Graph-ResNet together with GCN and convolutional neural network (CNN) benchmark models on Moscow traffic data and use them to first predict the traffic in Moscow and then to predict the traffic in Berlin and Istanbul. The results suggest that the graph-based models have superior generalization properties than CNN-based models for this application. We argue that in contrast to purely image-based approaches, formulating the prediction problem on a graph allows the neural network to learn properties given by the underlying street network. This facilitates the transfer of a learned network to predict the traffic status at unknown locations.} }
Endnote
%0 Conference Paper %T Graph-ResNets for short-term traffic forecasts in almost unknown cities %A Henry Martin %A Dominik Bucher %A Ye Hong %A René Buffat %A Christian Rupprecht %A Martin Raubal %B Proceedings of the NeurIPS 2019 Competition and Demonstration Track %C Proceedings of Machine Learning Research %D 2020 %E Hugo Jair Escalante %E Raia Hadsell %F pmlr-v123-martin20a %I PMLR %P 153--163 %U https://proceedings.mlr.press/v123/martin20a.html %V 123 %X The 2019 IARAI traffic4cast competition is a traffic forecasting problem based on traffic data from three cities that are encoded as images. We developed a ResNet-inspired graph convolutional neural network (GCN) approach that uses street network-based subgraphs of the image lattice graphs as a prior. We train the Graph-ResNet together with GCN and convolutional neural network (CNN) benchmark models on Moscow traffic data and use them to first predict the traffic in Moscow and then to predict the traffic in Berlin and Istanbul. The results suggest that the graph-based models have superior generalization properties than CNN-based models for this application. We argue that in contrast to purely image-based approaches, formulating the prediction problem on a graph allows the neural network to learn properties given by the underlying street network. This facilitates the transfer of a learned network to predict the traffic status at unknown locations.
APA
Martin, H., Bucher, D., Hong, Y., Buffat, R., Rupprecht, C. & Raubal, M.. (2020). Graph-ResNets for short-term traffic forecasts in almost unknown cities. Proceedings of the NeurIPS 2019 Competition and Demonstration Track, in Proceedings of Machine Learning Research 123:153-163 Available from https://proceedings.mlr.press/v123/martin20a.html.

Related Material