Equivariant Message Passing Neural Network for Crystal Material Discovery
This addresses the problem of limited geometric equivalence in crystal generation for material science, though it appears incremental as it builds on existing equivariant methods.
The paper tackles the challenge of unsupervised crystal material generation by proposing EMPNN, a periodic equivariant message-passing neural network that learns crystal lattice deformation without supervision, demonstrating effectiveness in experiments.
Automatic material discovery with desired properties is a fundamental challenge for material sciences. Considerable attention has recently been devoted to generating stable crystal structures. While existing work has shown impressive success on supervised tasks such as property prediction, the progress on unsupervised tasks such as material generation is still hampered by the limited extent to which the equivalent geometric representations of the same crystal are considered. To address this challenge, we propose EMPNN a periodic equivariant message-passing neural network that learns crystal lattice deformation in an unsupervised fashion. Our model equivalently acts on lattice according to the deformation action that must be performed, making it suitable for crystal generation, relaxation and optimisation. We present experimental evaluations that demonstrate the effectiveness of our approach.