Optimized Crystallographic Graph Generation for Material Science
This work addresses a computational bottleneck for researchers in material science using graph neural networks, though it is incremental as it focuses on optimization rather than a new method.
The authors tackled the problem of efficiently generating graph-based representations for crystalline materials in machine learning, proposing a GPU-optimized tool called pyMatGraph that enables real-time graph generation and updates during neural network training.
Graph neural networks are widely used in machine learning applied to chemistry, and in particular for material science discovery. For crystalline materials, however, generating graph-based representation from geometrical information for neural networks is not a trivial task. The periodicity of crystalline needs efficient implementations to be processed in real-time under a massively parallel environment. With the aim of training graph-based generative models of new material discovery, we propose an efficient tool to generate cutoff graphs and k-nearest-neighbours graphs of periodic structures within GPU optimization. We provide pyMatGraph a Pytorch-compatible framework to generate graphs in real-time during the training of neural network architecture. Our tool can update a graph of a structure, making generative models able to update the geometry and process the updated graph during the forward propagation on the GPU side. Our code is publicly available at https://github.com/aklipf/mat-graph.