Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs

Martin Simonovsky, Nikos Komodakis; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 3693-3702

Abstract


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. Together with the proper choice of graph coarsening, we explore constructing deep neural networks for graph classification. In particular, we demonstrate the generality of our formulation in point cloud classification, where we set the new state of the art, and on a graph classification dataset, where we outperform other deep learning approaches.

Related Material


[pdf] [supp] [arXiv] [poster] [video]
[bibtex]
@InProceedings{Simonovsky_2017_CVPR,
author = {Simonovsky, Martin and Komodakis, Nikos},
title = {Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {July},
year = {2017}
}