How Powerful are Graph Neural Networks?
Keyulu Xu, Weihua Hu, Jure Leskovec et al.
2018 · arXiv (Cornell University) · 2,728 citations
Graph Neural Networks (GNNs) are an effective framework for representation learning of graphs. GNNs follow a neighborhood aggregation scheme, where the representation vector of a node is computed by recursively aggregating and transforming representation vectors of its neighboring nodes. Many GNN variants have been proposed and have achieved state-of-the-art results on both node and graph classification tasks. However, despite GNNs revolutionizing graph representation learning, there is limited understanding of their representational properties and limitations. Here, we present a theoretical…
Explore this paper's citation graph on Constellation.