Machine learning (ML) models have been widely used to make predictions.

For a subclass of models, a finite number of densities suffice.

Motion planning is still an open problem for many disciplines, e.g., robotics, autonomous driving, due to their need for high computational resources that hinder

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