Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs

CVPR 2017 Martin Simonovsky • Nikos Komodakis

A number of problems can be formulated as prediction on graph-structured data. In this work, we generalize the convolution operator from regular grids to arbitrary graphs while avoiding the spectral domain, which allows us to handle graphs of varying size and connectivity. To move beyond a simple diffusion, filter weights are conditioned on the specific edge labels in the neighborhood of a vertex.

Full paper


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