https://openreview.net/forum?id=OIvg3MqWX2
A Theoretically-Principled Sparse, Connected, and Rigid Graph Representation of Molecules |...
Graph neural networks (GNNs) -- learn graph representations by exploiting the graph's sparsity, connectivity, and symmetries -- have become indispensable for...
rigid graphtheoreticallyprincipledsparseconnected
https://openreview.net/forum?id=J7Uh781A05p
Learning rigid dynamics with face interaction graph networks | OpenReview
Face to face, multi-index collisions improve accuracy and efficiency of graph network models for rigid body dynamics
learningrigiddynamicsfaceinteraction