e3nn: Euclidean Neural Networks
By Mario Geiger, Tess E. Smidt. 2022
301 citations recorded by the source corpus.
We present e3nn, a generalized framework for creating E(3) equivariant trainable functions, also known as Euclidean neural networks. e3nn naturally operates on geometry and geometric tensors that describe systems in 3D and transform predictably under a change of coordinate system. The core of e3nn are equivariant operations such as the TensorProduct class or the spherical harmonics functions that can be composed to create more complex modules such as convolutions and attention mechanisms. These core operations of e3nn can be used to efficiently articulate Tensor Field Networks, 3D Steerable CNNs, Clebsch-Gordan Networks, SE(3) Transformers and other E(3) equivariant networks.
Subfields: Artificial Intelligence, Biomedical Engineering, Computational Mechanics
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Tommi S. Jaakkola
- Regina Barzilay
- Quoc V. Le
- Percy Liang
- Ekin Dogus Cubuk
- Greg Yang
- Sam Schoenholz
- Amil Merchant
In Biomedical Engineering
In Computational Mechanics
Citations in the corpus
- DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking (2022, background): “…a convolutional filter T g for each bond g from the tensor product of the spherical harmonics with a ℓ = 2 representation of the bond axis ˆ r g : ⊗ is the full (i.e., unweighted) tensor product as described in [23], and the second term contains the spherical harmonics up to ℓ = 2 (as usual).”
- A foundation model for atomistic materials chemistry. (2023, unknown): “MACE All models trained in the paper use the MACE ( 35 ) architecture implemented in PyTorch ( 119 ) and employing the e3nn library ( 120 ).”
- Scaling deep learning for materials discovery (2023, methodology): “We train a NequIP potential 30 , implemented in JAX using the e3nn-jax library 66 , with five layers, hidden features of 128 ℓ = 0 scalars, 64 ℓ = 1 vectors and 32 ℓ = 2 tensors (all even irreducible representations only, 128 x 0 e + 64 x 1 x + 32 x 2 e ), as well as an edge-irreducible…”