Yuexin Zou

MatUQ: a benchmark for uncertainty-aware out-of-distribution materials property prediction with graph neural networks

This work introduces MatUQ, a benchmark built on structure-aware Smooth Overlap of Atomic Positions Leave-One-Cluster-Out (SOAP-LOCO) splitting, together with a training protocol that combines Deep Evidential Regression (DER) with dropout regularization, for evaluating GNN reliability under structural distribution shifts.