Improving Molecular Modeling with Geometric GNNs: an Empirical Study

Ali Ramlaoui, Théo Saulus, Basile Terver, Victor Schmidt, David Rolnick, Fragkiskos D. Malliaros, Alexandre AGM Duval

Keywords: equivariance, geometry, materials, gnn, deep_learning, oc20

TL;DR: An empirical study on Geometric Graph Neural Networks for 3D atomic systems focusing on the impact of different canonicalization methods, graph creation strategies, and auxiliary tasks

Abstract: Rapid advancements in machine learning (ML) are transforming materials science by significantly speeding up material property calculations. However, the proliferation of ML approaches has made it challenging for scientists to keep up with the most promising techniques. This paper presents an empirical study on Geometric Graph Neural Networks for 3D atomic systems, focusing on the impact of different (1) canonicalization methods, (2) graph creation strategies, and (3) auxiliary tasks, on performance, scalability and symmetry enforcement. Our findings and insights aim to guide researchers in selecting optimal modeling components for molecular modeling tasks.

Submission Number: 120