Residual Gated Graph ConvNets

ICLR 2018 Xavier Bresson • Thomas Laurent

In this paper, we are interested to design neural networks for graphs with variable length in order to solve learning problems such as vertex classification, graph classification, graph regression, and graph generative tasks. We review existing graph RNN and ConvNet architectures, and propose natural extension of LSTM and ConvNet to graphs with arbitrary size. Then, we design a set of analytically controlled experiments on two basic graph problems, i.e. subgraph matching and graph clustering, to test the different architectures.

Full paper


No evaluation results yet. Help compare this paper to other papers by submitting the tasks and evaluation metrics from the paper.