Spatio-Spectral Graph Neural Networks Simon Geisler, Arthur Kosmala

Spatial Message Passing Graph Neural Networks (MPGNNs) are widely used for learning on graph-structured data. However, key limitations of ℓ -step MPGNNs are that their "receptive field" is typically limited to the ℓ-hop neighborhood of a node and that information exchange between distant nodes is limited by over-squashing.