Structured Sequence Modeling with Graph Convolutional Recurrent Networks

Youngjoo Seo, Michaël Defferrard, Pierre Vandergheynst, Xavier Bresson

Abstract: This paper introduces Graph Convolutional Recurrent Network (GCRN), a deep learning model able to predict structured sequences of data. Precisely, GCRN is a generalization of classical recurrent neural networks (RNN) to data structured by any arbitrary graph. Such structured sequences can be series of frames in videos, spatio-temporal measurements on a network of sensors, or random walks on a vocabulary graph for natural language modeling.The proposed model combines convolutional neural networks (CNN) on graphs to identify spatial structures and RNN to find dynamic patterns. We study two possible architectures of GCRN, and apply the models to two practical problems: predicting moving MNIST data, and modeling natural language with the Penn Treebank dataset. Experiments show that exploiting simultaneously graph spatial and dynamic information about data can improve both precision and learning speed.

TL;DR: This paper introduces a neural network to model graph-structured sequences

Keywords: Structured prediction

Conflicts: epfl.ch, ntu.sg

Community Implementations: [ 7 code implementations](https://www.catalyzex.com/paper/arxiv:1612.07659/code)