构建材料属性预测的泛化评估框架，提升模型不确定性感知能力。
Benchmarking GNNs for OOD Materials Property Prediction with Uncertainty Quantification
- 提出SOAP-LOCO分割策略，更好捕捉原子局部环境
- 统一训练协议使误差平均降低70.6%
- 新指标D-EviU与预测误差相关性最强
我们提出MatUQ，一个用于评估图神经网络（GNN）在材料属性外分布（OOD）预测中不确定性量化（UQ）性能的基准框架。MatUQ包含1,375个来自六个材料数据集的OOD预测任务，采用五种基于OFM的方法和一种新提出的结构感知分割策略SOAP-LOCO，更有效捕捉局部原子环境。我们在统一的不确定性感知训练协议下评估12种代表性GNN模型，该协议结合蒙特卡洛丢弃与深度证据回归（DER），并引入新指标D-EviU，其在多数任务中与预测误差相关性最强。实验发现：第一，不确定性感知训练显著提升预测精度，在挑战性OOD场景下平均误差降低70.6%；第二，无单一模型始终领先：早期模型如SchNet和ALIGNN仍具竞争力，而CrystalFramer和SODNet在特定材料属性上表现更优。结果为材料发现中分布偏移下的模型选择提供实用参考。
原文摘要 · Abstract (English)
We present MatUQ, a benchmark framework for evaluating graph neural networks (GNNs) on out-of-distribution (OOD) materials property prediction with uncertainty quantification (UQ). MatUQ comprises 1,375 OOD prediction tasks constructed from six materials datasets using five OFM-based and a newly proposed structure-aware splitting strategy, SOAP-LOCO, which captures local atomic environments more effectively. We evaluate 12 representative GNN models under a unified uncertainty-aware training protocol that combines Monte Carlo Dropout and Deep Evidential Regression (DER), and introduce a novel uncertainty metric, D-EviU, which shows the strongest correlation with prediction errors in most tasks. Our experiments yield two key findings. First, the uncertainty-aware training approach significantly improves model prediction accuracy, reducing errors by an average of 70.6\% across challenging OOD scenarios. Second, the benchmark reveals that no single model dominates universally: earlier models such as SchNet and ALIGNN remain competitive, while newer models like CrystalFramer and SODNet demonstrate superior performance on specific material properties. These results provide practical insights for selecting reliable models under distribution shifts in materials discovery.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。