GemNet: Universal Directional Graph Neural Networks for Molecules. (arXiv:2106.08903v6 [physics.comp-ph] UPDATED)

Effectively predicting molecular interactions has the potential to accelerate
molecular dynamics by multiple orders of magnitude and thus revolutionize
chemical simulations. Graph neural networks (GNNs) have recently shown great
successes for this task, overtaking classical methods based on fixed molecular
kernels. However, they still appear very limited from a theoretical
perspective, since regular GNNs cannot distinguish certain types of graphs. In
this work we close this gap between theory and practice. We show that GNNs with
directed edge embeddings and …

arxiv graph graph neural networks networks neural networks physics