Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Complete and Efficient Graph Transformers for Crystal Material Property Prediction

About

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).

Keqiang Yan, Cong Fu, Xiaofeng Qian, Xiaoning Qian, Shuiwang Ji• 2024

Related benchmarks

TaskDatasetResultRank
Crystal Property PredictionJARVIS (test)
Formation Energy MAE (eV/atom)27.2
23
Crystal Property PredictionMaterials Project (MP)
Formation Energy MAE0.018
22
Crystal Property PredictionJARVIS-DFT (80/10/10 split)
Formation Energy MAE0.027
19
Crystal Property PredictionMaterials Project (test)
MAE Formation Energy (meV/atom)18.16
12
Property PredictionMatBench e_form-132752 (test)
MAE16.5
7
Property PredictionMatBench jdft2d-636 (test)
MAE34.8
7
Formation energy predictionJarvis
Time/Epoch59
7
Ionic Transport PredictionDataset 1 Trajectory-Based (test)
MAE (600K)0.451
5
Showing 8 of 8 rows

Other info

Follow for update