Improving the Long-Range Performance of Gated Graph Neural Networks

Graph Neural Networks (GNN) form a class of neural network architectures specifically designed to work with graphstructured data. In our work, we focus on multi-relational graphs, where edges are labeled with different edge types. While different GNN variants have been proposed in recent literature, to the best of our knowledge, their ability to capture long-term dependencies in graph data has not been thoroughly investigated. Due to their local aggregation nature, many layers of a GNN must be used to capture long-range patterns (i.e., at least K GNN layers are needed to incorporate any information from a node that is K hops away in the graph). However, GNNs suffer from decreasing performance when the number of layers is increased.