Many popular variants of graph neural networks (GNNs) that are capable of handling multi-relational graphs may suffer from vanishing gradients. In this work, we propose a novel GNN architecture based on the Gated Graph Neural Network with an improved ability to handle long-range dependencies in multi-relational graphs. An experimental analysis on different synthetic tasks demonstrates that the proposed architecture outperforms several popular GNN models.
@article{arxiv.2007.09668,
title = {Improving the Long-Range Performance of Gated Graph Neural Networks},
author = {Denis Lukovnikov and Jens Lehmann and Asja Fischer},
journal= {arXiv preprint arXiv:2007.09668},
year = {2020}
}