Complete and Efficient Graph Transformers for Crystal Material Property Prediction

TL;DR

This paper introduces ComFormer, a novel SE(3) transformer architecture tailored for crystal property prediction, effectively capturing the complete geometric information of crystals and handling chiral structures with state-of-the-art accuracy.

Contribution

The paper presents a new lattice-based graph representation for crystals and a specialized SE(3) transformer, ComFormer, with invariant and equivariant variants for improved crystal property prediction.

Findings

ComFormer achieves state-of-the-art results on multiple crystal benchmarks.

The lattice-based representation effectively captures periodic crystal structures.

ComFormer variants outperform existing methods in predictive accuracy.

Abstract

Crystal structures are characterized by atomic bases within a primitive unit cell that repeats along a regular lattice throughout 3D space. The periodic and infinite nature of crystals poses unique challenges for geometric graph representation learning. Specifically, constructing graphs that effectively capture the complete geometric information of crystals and handle chiral crystals remains an unsolved and challenging problem. In this paper, we introduce a novel approach that utilizes the periodic patterns of unit cells to establish the lattice-based representation for each atom, enabling efficient and expressive graph representations of crystals. Furthermore, we propose ComFormer, a SE(3) transformer designed specifically for crystalline materials. ComFormer includes two variants; namely, iComFormer that employs invariant geometric descriptors of Euclidean distances and angles, and eComFormer that utilizes equivariant vector representations. Experimental results demonstrate the state-of-the-art predictive accuracy of ComFormer variants on various tasks across three widely-used crystal benchmarks. Our code is publicly available as part of the AIRS library (https://github.com/divelab/AIRS).