Message-passing has proved to be an effective way to design graph neural networks, as it is
able to leverage both permutation equivariance and an inductive bias towards learning local …

Abstract Graph Neural Networks (GNNs), neural network architectures targeted to learning
representations of graphs, have become a popular learning model for prediction tasks on …

We study properties of Graph Convolutional Networks (GCNs) by analyzing their behavior
on standard models of random graphs, where nodes are represented by random latent …

A hallmark of graph neural networks is their ability to distinguish the isomorphism class of
their inputs. This study derives hardness results for the classification variant of graph …

We study the approximation power of Graph Neural Networks (GNNs) on latent position
random graphs. In the large graph limit, GNNs are known to converge to …

Graph neural networks (GNNs) have been successful in learning representations from
graphs. Many popular GNNs follow the pattern of aggregate-transform: they aggregate the …

We study the convergence of message passing graph neural networks on random graph
models to their continuous counterpart as the number of nodes tends to infinity. Until now …

This paper derives statistical guarantees for the performance of Graph Neural Networks
(GNNs) in link prediction tasks on graphs generated by a graphon. We propose a linear …

Graph convolutional networks (GCNs) are a widely used method for graph representation
learning. To elucidate their capabilities and limitations for graph classification, we …

Graph convolutional networks (GCNs) are a widely used method for graph representation
learning. To elucidate the capabilities and limitations of GCNs, we investigate their power …