Gated Graph Convolutional Recurrent Neural Networks

Graph processes model a number of important problems such as identifying the epicenter of an earthquake or predicting weather. In this paper, we propose a Graph Convolutional Recurrent Neural Network (GCRNN) architecture specifically tailored to deal with these problems. GCRNNs use convolutional filter banks to keep the number of trainable parameters independent of the size of the graph and of the time sequences considered. We also put forward Gated GCRNNs, a time-gated variation of GCRNNs akin to LSTMs. When compared with GNNs and another graph recurrent architecture in experiments using both synthetic and real-word data, GCRNNs significantly improve performance while using considerably less parameters.

[1]  Georgios B. Giannakis,et al.  A Recurrent Graph Neural Network for Multi-relational Data , 2018, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[2]  Yonina C. Eldar,et al.  A unified view of diffusion maps and signal processing on graphs , 2017, 2017 International Conference on Sampling Theory and Applications (SampTA).

[3]  Charles Elkan,et al.  Learning to Diagnose with LSTM Recurrent Neural Networks , 2015, ICLR.

[4]  Lakshmi S. Iyer,et al.  Business Analytics in the Context of Big Data: A Roadmap for Research , 2015, Commun. Assoc. Inf. Syst..

[5]  José M. F. Moura,et al.  Discrete Signal Processing on Graphs , 2012, IEEE Transactions on Signal Processing.

[6]  Thomas G. Dietterich.  Adaptive computation and machine learning , 1998 .

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

[8]  Alejandro Ribeiro,et al.  Ergodicity in Stationary Graph Processes: A Weak Law of Large Numbers , 2018, IEEE Transactions on Signal Processing.

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

[10]  Andreas Loukas,et al.  A Time-Vertex Signal Processing Framework: Scalable Processing and Meaningful Representations for Time-Series on Graphs , 2017, IEEE Transactions on Signal Processing.

[11]  Santiago Segarra,et al.  Optimal Graph-Filter Design and Applications to Distributed Linear Network Operators , 2017, IEEE Transactions on Signal Processing.

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

[13]  C.-C. Jay Kuo.  The CNN as a Guided Multilayer RECOS Transform [Lecture Notes] , 2017, IEEE Signal Processing Magazine.

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

[15]  Antonio G. Marques,et al.  Convolutional Neural Network Architectures for Signals Supported on Graphs , 2018, IEEE Transactions on Signal Processing.

[16]  Alejandro Ribeiro,et al.  Median Activation Functions for Graph Neural Networks , 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[17]  Pierre Vandergheynst,et al.  Stationary Signal Processing on Graphs , 2016, IEEE Transactions on Signal Processing.

[18]  Hao Ma,et al.  GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs , 2018, UAI.

[19]  Pascal Frossard,et al.  The emerging field of signal processing on graphs: Extending high-dimensional data analysis to networks and other irregular domains , 2012, IEEE Signal Processing Magazine.

[20]  Cyrus Shahabi,et al.  Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting , 2017, ICLR.