<ul><li>Atomistic materials modeling is a critical task with wide-ranging applications, from drug discovery to materials science.</li><li>Graph Neural Networks (GNNs) are widely used for atomistic materials modeling due to their ability to capture complex relational structures.</li><li>To address the gap in size and performance compared to large language models, a foundational GNN model with billions of parameters was developed and trained on terabyte-scale datasets.</li><li>The study explores the scaling laws for GNNs, provides insights into the relationship between model size, dataset volume, and accuracy, and enhances the GNN codebase with advanced training techniques.</li></ul>

Scaling Laws of Graph Neural Networks for Atomistic Materials Modeling

Discover more