Rotation-equivariant Graph Neural Networks for Learning Glassy Liquids Representations
This work addresses the challenge of relating static structure to dynamics in glassy liquids, offering a more robust and interpretable machine learning approach for researchers in materials science and physics.
The authors tackled the problem of predicting dynamics from static structure in glassy liquids by developing a rotation-equivariant Graph Neural Network (GNN) that preserves SE(3) equivariance, resulting in improved predictive power, better generalization to unseen temperatures, and enhanced interpretability compared to existing GNNs.
The difficult problem of relating the static structure of glassy liquids and their dynamics is a good target for Machine Learning, an approach which excels at finding complex patterns hidden in data. Indeed, this approach is currently a hot topic in the glassy liquids community, where the state of the art consists in Graph Neural Networks (GNNs), which have great expressive power but are heavy models and lack interpretability. Inspired by recent advances in the field of Machine Learning group-equivariant representations, we build a GNN that learns a robust representation of the glass' static structure by constraining it to preserve the roto-translation (SE(3)) equivariance. We show that this constraint significantly improves the predictive power at comparable or reduced number of parameters but most importantly, improves the ability to generalize to unseen temperatures. While remaining a Deep network, our model has improved interpretability compared to other GNNs, as the action of our basic convolution layer relates directly to well-known rotation-invariant expert features. Through transfer-learning experiments displaying unprecedented performance, we demonstrate that our network learns a robust representation, which allows us to push forward the idea of a learned structural order parameter for glasses.