Abstract
We present a materials generation framework that couples a symmetry-conditioned variational autoencoder with a differentiable SO(3) power spectrum objective to steer candidates toward a specified local environment under the crystallographic constraints. In particular, we implement a fully differentiable pipeline that performs batch-wise optimization on both direct and latent crystallographic representations. Using the GPU acceleration, the implementation achieves about fivefold speed compared to our previous CPU workflow, while yielding comparable outcomes. In addition, we introduce the optimization strategy that alternatively performs optimization on the direct and latent crystal representations. This dual-level relaxation approach can effectively escape local minima defined by different objective gradients, thus increasing the success rate of generating complex structures satisfying the target local environments. This framework can be extended to systems consisting of multi-components and multi-environments, providing a scalable route to generate material structures with the target local environment.
Funding Information
  • Basic Energy Sciences (DE-SC0024866)
  • French Government / ANR program “Investissements d’Avenir (ANR-18-EURE-0010)
  • UNC Charlotte seed grant for data science
  • European Commission
  • Conseil Régional Aquitaine
  • Poitiers University

This publication has 37 references indexed in Scilit: