2026-10-13T12:24:55Z https://api.figshare.com/v2/oai

oai:figshare.com:article/33869527 2026-09-17T02:50:36Z category_29161 category_26749 item_type_3 month_year_09_2026

DefectGNN-training graphs Yuqing Huang (24986050) Deep learning Materials engineering not elsewhere classified Graph Neural Network Approach DefectGNN Vacancy defects <p dir="ltr">This dataset contains the processed graph inputs and corresponding target labels used to train, validate, and independently evaluate the primary DefectGNN model. The data represent equiatomic atomic configurations encoded as graph for graph neural network regression.</p><p dir="ltr">Each dataset includes a CSV file listing the serialized graph files and a corresponding pickle file containing the target labels. The training dataset additionally includes the fixed training, validation, and empty internal-test index files used for the reported model split.</p><p dir="ltr">The associated DefectGNN source code, training configuration, and prediction script are available from <a href="https://github.com/Yuqing-Huang-mse/DefectGNN" target="_blank">Yuqing-Huang-mse/DefectGNN</a></p> 2026-09-17T02:50:36Z Dataset Dataset 10.6084/m9.figshare.33869527.v1 https://figshare.com/articles/dataset/DefectGNN-training_graphs/33869527 CC BY 4.0