While message-passing graph neural networks have clear limitations in approximating
permutation-equivariant functions over graphs or general relational data, more expressive …

The invariance to permutations of the adjacency matrix, ie, graph isomorphism, is an
overarching requirement for Graph Neural Networks (GNNs). Conventionally, this …

While Graph Neural Networks (GNNs) have achieved remarkable results in a variety of
applications, recent studies exposed important shortcomings in their ability to capture the …

Abstract Graph Neural Networks (GNNs) are attracting growing attention due to their
effectiveness and flexibility in modeling a variety of graph-structured data. Exiting GNN …

Graph neural networks (GNNs) have emerged recently as a powerful architecture for
learning node and graph representations. Standard GNNs have the same expressive power …

Graph neural networks (GNNs) have achieved tremendous success on multiple graph-
based learning tasks by fusing network structure and node features. Modern GNN models …

Graph Neural Networks (GNNs) are an effective framework for representation learning of
graphs. GNNs follow a neighborhood aggregation scheme, where the representation vector …

Despite recent advances in representation learning in hypercomplex (HC) space, this
subject is still vastly unexplored in the context of graphs. Motivated by the complex and …

Recent advances in representation learning on graphs, mainly leveraging graph
convolutional networks, have brought a substantial improvement on many graph-based …

This work generalizes graph neural networks (GNNs) beyond those based on the Weisfeiler-
Lehman (WL) algorithm, graph Laplacians, and diffusions. Our approach, denoted …