A common approach to create more expressive GNNs is to change the message passing function of MPNNs. If a GNN is more expressive than MPNNs by adapting the message passing function, we call this non-standard message passing . Examples of this are message passing variants that operate on subgraphs [Frasca et al., 2022, Bevilacqua

We introduce Automorphism-based graph neural networks (Autobahn), a new familyofgraphneuralnetworks.

MAG-GNN effectively reduces the running time of subgraph GNNs.

Recently, several equivariant message passing neural networks (MPNNs) have been shown to outperform models built using otherapproaches intermsofaccuracy.