We lifted 2 functions out of this paper's own repositories and ran 2 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| copy not recorded | — | 2 of 2 |
| Function | Status | Where it lives |
|---|---|---|
| pack_one | Ran | this paper's copy was not recorded; identical code first harvested from lucidrains/equiformer-pytorch pointer only · get_code("122e87ee0b05894f") |
| unpack_one | Ran | this paper's copy was not recorded; identical code first harvested from lucidrains/equiformer-pytorch pointer only · get_code("b8149022c0d28e97") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Graph neural networks that model 3D data, such as point clouds or atoms, are typically desired to be $SO(3)$ equivariant, i.e., equivariant to 3D rotations. Unfortunately equivariant convolutions, which are a fundamental operation for equivariant networks, increase significantly in computational complexity as higher-order tensors are used. In this paper, we address this issue by reducing the $SO(3)$ convolutions or tensor products to mathematically equivalent convolutions in $SO(2)$ . This is accomplished by aligning the node embeddings' primary axis with the edge vectors, which sparsifies the tensor product and reduces the computational complexity from $O(L^6)$ to $O(L^3)$, where $L$ is the degree of the representation. We demonstrate the potential implications of this improvement by proposing the Equivariant Spherical Channel Network (eSCN), a graph neural network utilizing our novel approach to equivariant convolutions, which achieves state-of-the-art results on the large-scale OC-20 and OC-22 datasets.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2302.03655")
get_code_for_paper("2302.03655")
have("2302.03655")
Connect an agent — have() is free.