Relational Fusion Networks: Graph Convolutional Networks for Road Networks

The application of machine learning techniques in the setting of road networks holds the potential to facilitate many important intelligent transportation applications. Graph Convolutional Networks (GCNs) are neural networks that are capable of leveraging the structure of a network. However, many implicit assumptions of GCNs do not apply to road networks. We introduce the Relational Fusion Network (RFN), a novel type of GCN designed specifically for road networks. In particular, we propose methods that outperform state-of-the-art GCNs by 21%-40% on two machine learning tasks in road networks. Furthermore, we show that state-of-the-art GCNs may fail to effectively leverage road network structure and may not generalize well to other road networks.

[1]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[2]  Bin Guo,et al.  An Attention-Based User Profiling Model by Leveraging Multi-modal Social Media Contents , 2019, Communications in Computer and Information Science.

[3]  Laurens van der Maaten,et al.  Accelerating t-SNE using tree-based algorithms , 2014, J. Mach. Learn. Res..

[4]  Christian S. Jensen,et al.  Graph Convolutional Networks for Road Networks , 2019, SIGSPATIAL/GIS.

[5]  Xavier Bresson,et al.  Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering , 2016, NIPS.

[6]  Zibin Zheng,et al.  Deep and Embedded Learning Approach for Traffic Flow Prediction in Urban Informatics , 2019, IEEE Transactions on Intelligent Transportation Systems.

[7]  Joan Bruna,et al.  Spectral Networks and Locally Connected Networks on Graphs , 2013, ICLR.

[8]  Jiujun Cheng,et al.  Long-Term Traffic Speed Prediction Based on Multiscale Spatio-Temporal Feature Learning Network , 2019, IEEE Transactions on Intelligent Transportation Systems.

[9]  Ove Andersen,et al.  An Open-Source Based ITS Platform , 2013, 2013 IEEE 14th International Conference on Mobile Data Management.

[10]  Yoshua Bengio,et al.  Deep Sparse Rectifier Neural Networks , 2011, AISTATS.

[11]  Christian S. Jensen,et al.  Stochastic Weight Completion for Road Networks Using Graph Convolutional Networks , 2019, 2019 IEEE 35th International Conference on Data Engineering (ICDE).

[12]  Zheng Wang,et al.  Multi-task Representation Learning for Travel Time Estimation , 2018, KDD.

[13]  Cao Xiao,et al.  FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling , 2018, ICLR.

[14]  Xavier Bresson,et al.  CayleyNets: Graph Convolutional Neural Networks With Complex Rational Spectral Filters , 2017, IEEE Transactions on Signal Processing.

[15]  Fei-Yue Wang,et al.  Traffic Flow Prediction With Big Data: A Deep Learning Approach , 2015, IEEE Transactions on Intelligent Transportation Systems.

[16]  Jure Leskovec,et al.  Inductive Representation Learning on Large Graphs , 2017, NIPS.

[17]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[18]  Yu Liu,et al.  T-GCN: A Temporal Graph Convolutional Network for Traffic Prediction , 2018, IEEE Transactions on Intelligent Transportation Systems.

[19]  Yizhou Sun,et al.  Layer-Dependent Importance Sampling for Training Deep and Large Graph Convolutional Networks , 2019, NeurIPS.

[20]  Pietro Liò,et al.  Graph Attention Networks , 2017, ICLR.

[21]  Guiyuan Jiang,et al.  Travel-Time Prediction of Bus Journey With Multiple Bus Trips , 2019, IEEE Transactions on Intelligent Transportation Systems.

[22]  Zhanxing Zhu,et al.  Spatio-temporal Graph Convolutional Neural Network: A Deep Learning Framework for Traffic Forecasting , 2017, IJCAI.

[23]  Christian S. Jensen,et al.  On Network Embedding for Machine Learning on Road Networks: A Case Study on the Danish Road Network , 2018, 2018 IEEE International Conference on Big Data (Big Data).

[24]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[25]  Junzhou Huang,et al.  Adaptive Sampling Towards Fast Graph Representation Learning , 2018, NeurIPS.

[26]  Sepp Hochreiter,et al.  Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs) , 2015, ICLR.