Vector Field Oriented Diffusion Model for Crystal Material Generation
This work addresses a domain-specific problem in material science for researchers, but it appears incremental as it builds on existing diffusion models and benchmarks.
The authors tackled the problem of generating new crystal structures with specific chemical properties by proposing a diffusion model that jointly considers atomic positions and crystal lattices using a geometrically equivariant GNN. Their experiments on existing benchmarks demonstrated the model's effectiveness, though no concrete numbers were provided in the abstract.
Discovering crystal structures with specific chemical properties has become an increasingly important focus in material science. However, current models are limited in their ability to generate new crystal lattices, as they only consider atomic positions or chemical composition. To address this issue, we propose a probabilistic diffusion model that utilizes a geometrically equivariant GNN to consider atomic positions and crystal lattices jointly. To evaluate the effectiveness of our model, we introduce a new generation metric inspired by Frechet Inception Distance, but based on GNN energy prediction rather than InceptionV3 used in computer vision. In addition to commonly used metrics like validity, which assesses the plausibility of a structure, this new metric offers a more comprehensive evaluation of our model's capabilities. Our experiments on existing benchmarks show the significance of our diffusion model. We also show that our method can effectively learn meaningful representations.