We propose an extension of Convolutional Neural Networks (CNNs) to graph-structured data, including strided convolutions and data augmentation on graphs. Our method matches the accuracy of state-of-the-art CNNs when applied on images, without any prior about their 2D regular structure. On fMRI data, we obtain a significant gain in accuracy compared with existing graph-based alternatives.
@article{arxiv.1802.09802,
title = {Matching Convolutional Neural Networks without Priors about Data},
author = {Carlos Eduardo Rosar Kos Lassance and Jean-Charles Vialatte and Vincent Gripon},
journal= {arXiv preprint arXiv:1802.09802},
year = {2018}
}