Structured Sequence Modeling with Graph Convolutional Recurrent Networks
This work addresses the need for modeling structured sequences in domains like video analysis and natural language processing, representing an incremental advancement by generalizing existing methods to graph-structured data.
The paper tackles the problem of predicting structured sequences of data, such as videos or sensor networks, by introducing the Graph Convolutional Recurrent Network (GCRN), which combines graph convolutional neural networks and recurrent neural networks to model spatial and dynamic patterns, resulting in improved precision and learning speed in experiments on moving MNIST and Penn Treebank datasets.
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 an arbitrary graph. Such structured sequences can represent 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.