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 …

In recent years, algorithms and neural architectures based on the Weisfeiler-Leman
algorithm, a well-known heuristic for the graph isomorphism problem, have emerged as a …

Abstract Graph Neural Networks (GNN) are inherently limited in their expressive power.
Recent seminal works (Xu et al., 2019; Morris et al., 2019b) introduced the Weisfeiler …

Vector representations of graphs and relational structures, whether hand-crafted feature
vectors or learned representations, enable us to apply standard data analysis and machine …

Graph neural networks (GNNs) are deep learning architectures for machine learning
problems on graphs. It has recently been shown that the expressiveness of GNNs can be …

Graph kernels based on the $1 $-dimensional Weisfeiler-Leman algorithm and
corresponding neural architectures recently emerged as powerful tools for (supervised) …

Various recent proposals increase the distinguishing power of Graph Neural Networks
(GNNs) by propagating features between k-tuples of vertices. The distinguishing power of …

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

Recently, many works studied the expressive power of graph neural networks (GNNs) by
linking it to the $1 $-dimensional Weisfeiler-Leman algorithm ($1\text {-}\mathsf {WL} $) …

Numerous recent works have analyzed the expressive power of message-passing graph
neural networks (MPNNs), primarily utilizing combinatorial techniques such as the $1 …