AreHigh-DegreeRepresentations Really Unnecessary inEquivariantGraphNeuralNetworks?
–Neural Information Processing Systems
Asoneofthe most successful models, EGNN [1] leverages a simple scalarization technique to perform equivariant message passing over only Cartesian vectors (i.e., 1stdegree steerable vectors), enjoying greater efficiency and efficacy compared to equivariant GNNs using higher-degree steerable vectors.
Neural Information Processing Systems
Feb-10-2026, 11:59:54 GMT