Rethinking the expressive power of gnns via graph biconnectivity
Designing expressive Graph Neural Networks (GNNs) is a central topic in learning graph-
structured data. While numerous approaches have been proposed to improve GNNs in …
structured data. While numerous approaches have been proposed to improve GNNs in …
A complete expressiveness hierarchy for subgraph gnns via subgraph weisfeiler-lehman tests
Recently, subgraph GNNs have emerged as an important direction for developing
expressive graph neural networks (GNNs). While numerous architectures have been …
expressive graph neural networks (GNNs). While numerous architectures have been …
State of the Art and Potentialities of Graph-level Learning
Graphs have a superior ability to represent relational data, such as chemical compounds,
proteins, and social networks. Hence, graph-level learning, which takes a set of graphs as …
proteins, and social networks. Hence, graph-level learning, which takes a set of graphs as …
Wl meet vc
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} $) …
linking it to the $1 $-dimensional Weisfeiler-Leman algorithm ($1\text {-}\mathsf {WL} $) …
Mag-gnn: Reinforcement learning boosted graph neural network
Abstract While Graph Neural Networks (GNNs) recently became powerful tools in graph
learning tasks, considerable efforts have been spent on improving GNNs' structural …
learning tasks, considerable efforts have been spent on improving GNNs' structural …
Efficient subgraph gnns by learning effective selection policies
Subgraph GNNs are provably expressive neural architectures that learn graph
representations from sets of subgraphs. Unfortunately, their applicability is hampered by the …
representations from sets of subgraphs. Unfortunately, their applicability is hampered by the …
An Empirical Study of Realized GNN Expressiveness
Research on the theoretical expressiveness of Graph Neural Networks (GNNs) has
developed rapidly, and many methods have been proposed to enhance the expressiveness …
developed rapidly, and many methods have been proposed to enhance the expressiveness …
Beyond weisfeiler-lehman: A quantitative framework for GNN expressiveness
Designing expressive Graph Neural Networks (GNNs) is a fundamental topic in the graph
learning community. So far, GNN expressiveness has been primarily assessed via the …
learning community. So far, GNN expressiveness has been primarily assessed via the …
Simplifying subgraph representation learning for scalable link prediction
Link prediction on graphs is a fundamental problem. Subgraph representation learning
approaches (SGRLs), by transforming link prediction to graph classification on the …
approaches (SGRLs), by transforming link prediction to graph classification on the …
Weisfeiler-Leman at the margin: When more expressivity matters
The Weisfeiler-Leman algorithm ($1 $-WL) is a well-studied heuristic for the graph
isomorphism problem. Recently, the algorithm has played a prominent role in understanding …
isomorphism problem. Recently, the algorithm has played a prominent role in understanding …