Showing 2024Show all
2 papers · 1 filter
cs.LG2024
High-Rank Irreducible Cartesian Tensor Decomposition and Bases of Equivariant Spaces
Shihao Shao, Yikang Li, Zhouchen Lin +1
Irreducible Cartesian tensors (ICTs) play a crucial role in the design of equivariant graph neural networks, as well as in theoretical chemistry and chemical physics. Meanwhile, th…
cs.LG2024
Symmetry Discovery for Different Data Types
Lexiang Hu, Yikang Li, Zhouchen Lin
Equivariant neural networks incorporate symmetries into their architecture, achieving higher generalization performance. However, constructing equivariant neural networks typically…