-
Tensor Channel Equivariant Graph Neural Networks for Molecular...
This paper improves uponn the previous paper published at the NeurIPS '25 ML4PhysicalScience-Workshop by using overcomplete generating sets rather than a basis to represent... -
Discretizing Group-Convolutional Neural Networks for 3D Geometry in Feature...
A paper that describes how to speed-up deep learning on 3D point clouds with (G-)CNNs by compressing its linear representation layers by a local partial symmetry analysis. -
General Nonlinearities in SO(2)-Equivariant Networks (Paper)
Handling general nonlinearities in group-convolutional networks with SO(2)-invariance. -
Graph Neural Networks with Local Frames (Paper)
The paper describes a graph neural network architecture that uses local frames to predict local geometric properties..