Knowledge graph embedding (KGE) is an increasingly popular technique that aims to
represent entities and relations of knowledge graphs into low-dimensional semantic spaces …

Real-world data generation often involves complex inter-dependencies among instances,
violating the IID-data hypothesis of standard learning paradigms and posing a challenge for …

Graph neural networks (GNNs) are vulnerable to adversarial perturbations, including those
that affect both node features and graph topology. This paper investigates GNNs derived …

Abstract While Graph Neural Networks (GNNs) have recently become the de facto standard
for modeling relational data, they impose a strong assumption on the availability of the node …

Graph neural networks (GNNs) are one of the most popular research topics for deep
learning. GNN methods typically have been designed on top of the graph signal processing …

Hypergraph neural networks (HNNs) using neural networks to encode hypergraphs provide
a promising way to model higher-order relations in data and further solve relevant prediction …

Training graph neural networks (GNNs) on large graphs is complex and extremely time
consuming. This is attributed to overheads caused by sparse matrix multiplication, which are …

Gradient flows are differential equations that minimize an energy functional and constitute
the main descriptors of physical systems. We apply this formalism to Graph Neural Networks …

Recent studies reveal the connection between GNNs and the diffusion process, which
motivates many diffusion based GNNs to be proposed. However, since these two …

Abstract Graph Neural Networks (GNNs) are limited in their propagation operators. In many
cases, these operators often contain non-negative elements only and are shared across …