The last half-decade has seen a surge in deep learning research on irregular domains and
efforts to extend convolutional neural networks (CNNs) to work on irregularly structured data …

Many real-world datasets can be naturally represented as graphs, spanning a wide range of
domains. However, the increasing complexity and size of graph datasets present significant …

A number of problems can be formulated as prediction on graph-structured data. In this
work, we generalize the convolution operator from regular grids to arbitrary graphs while …

Can one reduce the size of a graph without significantly altering its basic properties? The
graph reduction problem is hereby approached from the perspective of restricted spectral …

We propose a novel graph cross network (GXN) to achieve comprehensive feature learning
from multiple scales of a graph. Based on trainable hierarchical representations of a graph …

Emerging quantum processors provide an opportunity to explore new approaches for
solving traditional problems in the post Moore's law supercomputing era. However, the …

Multilayer networks have been widely used to represent and analyze systems of
interconnected entities where both the entities and their connections can be of different …

Abstract How might one``reduce''a graph? That is, generate a smaller graph that preserves
the global structure at the expense of discarding local details? There has been extensive …

Graph convolutional networks (GCNs) have attracted increasing attention in recent years.
Many important tasks in graph analysis involve graph classification which aims to map a …

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 …