The Open MatSci ML Toolkit: A Flexible Framework for Machine Learning in Materials Science
This toolkit lowers the entry barrier for researchers working on materials science, particularly for clean energy applications, but it is incremental as it builds on existing tools like PyTorch Lightning and DGL.
The authors introduced the Open MatSci ML Toolkit, a flexible Python framework for applying deep learning to materials science, specifically using the OpenCatalyst Dataset, and demonstrated its capabilities by enabling three new equivariant neural network models with promising results for compute scaling and model performance.
We present the Open MatSci ML Toolkit: a flexible, self-contained, and scalable Python-based framework to apply deep learning models and methods on scientific data with a specific focus on materials science and the OpenCatalyst Dataset. Our toolkit provides: 1. A scalable machine learning workflow for materials science leveraging PyTorch Lightning, which enables seamless scaling across different computation capabilities (laptop, server, cluster) and hardware platforms (CPU, GPU, XPU). 2. Deep Graph Library (DGL) support for rapid graph neural network prototyping and development. By publishing and sharing this toolkit with the research community via open-source release, we hope to: 1. Lower the entry barrier for new machine learning researchers and practitioners that want to get started with the OpenCatalyst dataset, which presently comprises the largest computational materials science dataset. 2. Enable the scientific community to apply advanced machine learning tools to high-impact scientific challenges, such as modeling of materials behavior for clean energy applications. We demonstrate the capabilities of our framework by enabling three new equivariant neural network models for multiple OpenCatalyst tasks and arrive at promising results for compute scaling and model performance.