Gated Graph Convolutional Recurrent Neural Networks
This work addresses graph process modeling for applications such as disaster response and meteorology, representing an incremental advancement in graph neural network architectures.
The paper tackles the problem of modeling graph processes like earthquake epicenter identification and weather prediction by proposing a Graph Convolutional Recurrent Neural Network (GCRNN) architecture, which significantly improves performance while using considerably fewer parameters compared to existing methods.
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.