Constructing Invariant and Equivariant Operations by Symmetric Tensor Network
By: Meng Zhang , Chao Wang , Hao Zhang and more
Potential Business Impact:
Makes AI understand shapes and patterns better.
Design of neural networks that incorporate symmetry is crucial for geometric deep learning. Central to this effort is the development of invariant and equivariant operations. This works presents a systematic method for constructing valid invariant and equivariant operations. It can handle inputs and outputs in the form of Cartesian tensors with different rank, as well as spherical tensors with different types. In addition, our method features a graphical representation utilizing the symmetric tensor network, which simplifies both the proofs and constructions related to invariant and equivariant functions. We also apply this approach to design the equivariant interaction message for the geometry graph neural network, and equivariant machine learning model to learn the constitutive law of materials.
Similar Papers
Permutation Equivariant Neural Networks for Symmetric Tensors
Machine Learning (CS)
Teaches computers to understand patterns in nature.
A Complete Guide to Spherical Equivariant Graph Transformers
Machine Learning (CS)
Teaches computers to understand 3D shapes like molecules.
Representing spherical tensors with scalar-based machine-learning models
Chemical Physics
Makes computers understand 3D shapes better.