Rethinking the expressive power of gnns via graph biconnectivity

B Zhang, S Luo, L Wang, D He - arXiv preprint arXiv:2301.09505, 2023 - arxiv.org
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 …

A complete expressiveness hierarchy for subgraph gnns via subgraph weisfeiler-lehman tests

B Zhang, G Feng, Y Du, D He… - … Conference on Machine …, 2023 - proceedings.mlr.press
Recently, subgraph GNNs have emerged as an important direction for developing
expressive graph neural networks (GNNs). While numerous architectures have been …

State of the Art and Potentialities of Graph-level Learning

Z Yang, G Zhang, J Wu, J Yang, QZ Sheng… - ACM Computing …, 2024 - dl.acm.org
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 …

Wl meet vc

C Morris, F Geerts, J Tönshoff… - … Conference on Machine …, 2023 - proceedings.mlr.press
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} $) …

Mag-gnn: Reinforcement learning boosted graph neural network

L Kong, J Feng, H Liu, D Tao… - Advances in Neural …, 2024 - proceedings.neurips.cc
Abstract While Graph Neural Networks (GNNs) recently became powerful tools in graph
learning tasks, considerable efforts have been spent on improving GNNs' structural …

Efficient subgraph gnns by learning effective selection policies

B Bevilacqua, M Eliasof, E Meirom, B Ribeiro… - arXiv preprint arXiv …, 2023 - arxiv.org
Subgraph GNNs are provably expressive neural architectures that learn graph
representations from sets of subgraphs. Unfortunately, their applicability is hampered by the …

An Empirical Study of Realized GNN Expressiveness

Y Wang, M Zhang - Forty-first International Conference on Machine …, 2024 - openreview.net
Research on the theoretical expressiveness of Graph Neural Networks (GNNs) has
developed rapidly, and many methods have been proposed to enhance the expressiveness …

Beyond weisfeiler-lehman: A quantitative framework for GNN expressiveness

B Zhang, J Gai, Y Du, Q Ye, D He, L Wang - arXiv preprint arXiv …, 2024 - arxiv.org
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 …

Simplifying subgraph representation learning for scalable link prediction

P Louis, SA Jacob, A Salehi-Abari - arXiv preprint arXiv:2301.12562, 2023 - arxiv.org
Link prediction on graphs is a fundamental problem. Subgraph representation learning
approaches (SGRLs), by transforming link prediction to graph classification on the …

Weisfeiler-Leman at the margin: When more expressivity matters

BJ Franks, C Morris, A Velingker, F Geerts - arXiv preprint arXiv …, 2024 - arxiv.org
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 …