Accelerating Material Property Prediction using Generically Complete Isometry Invariants
This work addresses the problem of efficient material property prediction for researchers in materials science, offering a faster alternative to existing methods.
The authors tackled the challenge of representing periodic crystals for machine learning by adapting the Pointwise Distance Distribution (PDD) as a generically complete isometry invariant, and developed a transformer model that achieved accuracy on par with state-of-the-art methods while being several times faster in training and prediction.
Periodic material or crystal property prediction using machine learning has grown popular in recent years as it provides a computationally efficient replacement for classical simulation methods. A crucial first step for any of these algorithms is the representation used for a periodic crystal. While similar objects like molecules and proteins have a finite number of atoms and their representation can be built based upon a finite point cloud interpretation, periodic crystals are unbounded in size, making their representation more challenging. In the present work, we adapt the Pointwise Distance Distribution (PDD), a continuous and generically complete isometry invariant for periodic point sets, as a representation for our learning algorithm. The PDD distinguished all (more than 660 thousand) periodic crystals in the Cambridge Structural Database as purely periodic sets of points without atomic types. We develop a transformer model with a modified self-attention mechanism that combines PDD with compositional information via a spatial encoding method. This model is tested on the crystals of the Materials Project and Jarvis-DFT databases and shown to produce accuracy on par with state-of-the-art methods while being several times faster in both training and prediction time.