Graph Neural Networks for Learning Equivariant Representations of Neural Networks
Graph Neural Networks for Learning Equivariant Representations of Neural Networks
Latent Field Discovery in Interacting Dynamical Systems with Neural Fields
We discover global fields in interacting systems, inferring them from the dynamics alone, using neural fields.
Neural Networks Are Graphs! Graph Neural Networks for Equivariant Processing of Neural Networks
Neural Networks Are Graphs! Graph Neural Networks for Equivariant Processing of Neural Networks
David W. Zhang
Roto-translated Local Coordinate Frames For Interacting Dynamical Systems
Equivariance via canonicalized object-centric local frames in geometric graphs