MatSciML: A Broad, Multi-Task Benchmark for Solid-State Materials Modeling

1 code implementation • 12 Sep 2023 • Kin Long Kelvin Lee, Carmelo Gonzales, Marcel Nassar, Matthew Spellings, Mikhail Galkin, Santiago Miret

We propose MatSci ML, a novel benchmark for modeling MATerials SCIence using Machine Learning (MatSci ML) methods focused on solid-state materials with periodic crystal structures.

Atomic Forces Multi-Task Learning

Using Multiple Vector Channels Improves E(n)-Equivariant Graph Neural Networks

no code implementations • 6 Sep 2023 • Daniel Levy, Sékou-Oumar Kaba, Carmelo Gonzales, Santiago Miret, Siamak Ravanbakhsh

We present a natural extension to E(n)-equivariant graph neural networks that uses multiple equivariant vectors per node.

The Open MatSci ML Toolkit: A Flexible Framework for Machine Learning in Materials Science

1 code implementation • 31 Oct 2022 • Santiago Miret, Kin Long Kelvin Lee, Carmelo Gonzales, Marcel Nassar, Matthew Spellings

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.