PRISM: Periodic Representation with multIscale and Similarity graph Modelling for enhanced crystal structure property prediction

TL;DR

PRISM is a novel graph neural network framework that explicitly models periodic boundary conditions and multiscale interactions in crystal structures, leading to improved accuracy in property prediction.

Contribution

It introduces a set of expert modules for encoding multiscale and periodic features, advancing graph-based learning for crystalline materials.

Findings

PRISM outperforms existing models on crystal property benchmarks.

Explicit periodic and multiscale encoding improves prediction accuracy.

The framework effectively captures structural and chemical aspects of crystals.

Abstract

Crystal structures are characterised by repeating atomic patterns within unit cells across three-dimensional space, posing unique challenges for graph-based representation learning. Current methods often overlook essential periodic boundary conditions and multiscale interactions inherent to crystalline structures. In this paper, we introduce PRISM, a graph neural network framework that explicitly integrates multiscale representations and periodic feature encoding by employing a set of expert modules, each specialised in encoding distinct structural and chemical aspects of periodic systems. Extensive experiments across crystal structure-based benchmarks demonstrate that PRISM improves state-of-the-art predictive accuracy, significantly enhancing crystal property prediction.