Understanding Self-Assembly Behavior with Self-Supervised Learning

Recently, deep learning models trained on enormous amounts of data using simple language modeling tasks have shown great promise when applied to new problems, including the generation of novel text. These results have spurred the proliferation of attention mechanisms, which are particularly useful for their power and the ability to inspect model behavior by viewing attention weights for a given input. In this work, we show several permutation- and rotation-equivariant neural network architectures using attention mechanisms to solve self-supervised tasks on point clouds. We show how the representations learned by these networks can be applied to understand the impact of interactions on the structural evolution of systems of self-assembling particles. Equivariant architectures such as those shown here can help apply the power of deep learning to new applications in materials science, opening the door to powerful ways to analyze and even generate novel local environments within ordered structures.