We introduce a large-scale dataset of quantum-mechanically calculated properties of crystalline materials for graph representation learning that contains approximately 900k entries (OQM9HK). This dataset is constructed on the basis of the Open Quantum Materials Database (OQMD) v1.5 containing more than one million entries, and is the successor to the OQMD v1.2 dataset containing approximately 600k entries (OQM6HK). We develop the graph creation algorithm to produce a binary edge-labeled (BEL) graph representing a crystalline material. The BEL graph has higher representability of crystal structure than the edge-unlabeled ones. In materials property prediction tasks, crystal graph neural networks trained on the BEL graph dataset perform better than ones on the other graph datasets. The OQM9HK graph dataset is available at the Zenodo repository, https://doi.org/10.5281/zenodo.7124330
Machine learning methods have been employed for materials prediction in various ways. It has recently been proposed that a crystalline material is represented by a multigraph called a crystal graph. Convolutional neural networks adapted to those graphs have successfully predicted bulk properties of materials with the use of equilibrium bond distances as spatial information. An investigation into graph neural networks for small molecules has recently shown that the no distance model performs almost as well as the distance model. This paper proposes crystal graph neural networks (CGNNs) that use no bond distances, and introduces a scale-invariant graph coordinator that makes up crystal graphs for the CGNN models to be trained on the dataset based on a theoretical materials database. The CGNN models predict the bulk properties such as formation energy, unit cell volume, band gap, and total magnetization for every testing material, and the average errors are less than the corresponding ones of the database. The predicted band gaps and total magnetizations are used for the metal-insulator and nonmagnet-magnet binary classifications, which result in success. This paper presents discussions about high- throughput screening of candidate materials with the use of the predicted formation energies, and also about the future progress of materials data mining on the basis of the CGNN architectures.