用浅层集成提升GNN在材料预测中的不确定性判断能力
Uncertainty Quantification in Graph Neural Networks with Shallow Ensembles
- 在SchNet中引入浅层集成，高效计算预测不确定性
- 在QM9、OC20等数据集上成功识别出域外样本，域外预测不确定性更高
- 适合关注模型可靠性与主动学习的材料模拟研究者
机器学习势函数（MLPs）已革新材料发现，实现分子与材料性质的高精度、高效预测。图神经网络（GNN）因能捕捉复杂原子相互作用而成为前沿方法。然而，当面对域外数据时，GNN常产生不可靠预测，且难以识别此类情况。为此，本文探索不确定性量化（UQ）技术，聚焦于计算高效的浅层集成直接传播法（DPOSE），作为深度集成的替代方案。将DPOSE集成至SchNet模型，评估其在多种密度泛函理论数据集（包括QM9、OC20和金分子动力学数据）上提供可靠不确定性估计的能力。结果表明，DPOSE能有效区分域内与域外样本，在未观测分子与材料类别上表现出更高不确定性。本工作凸显了轻量级UQ方法在提升GNN基材料建模鲁棒性方面的潜力，并为未来与主动学习策略的结合奠定基础。
原文摘要 · Abstract (English)
Machine-learned potentials (MLPs) have revolutionized materials discovery by providing accurate and efficient predictions of molecular and material properties. Graph Neural Networks (GNNs) have emerged as a state-of-the-art approach due to their ability to capture complex atomic interactions. However, GNNs often produce unreliable predictions when encountering out-of-domain data and it is difficult to identify when that happens. To address this challenge, we explore Uncertainty Quantification (UQ) techniques, focusing on Direct Propagation of Shallow Ensembles (DPOSE) as a computationally efficient alternative to deep ensembles. By integrating DPOSE into the SchNet model, we assess its ability to provide reliable uncertainty estimates across diverse Density Functional Theory datasets, including QM9, OC20, and Gold Molecular Dynamics. Our findings often demonstrate that DPOSE successfully distinguishes between in-domain and out-of-domain samples, exhibiting higher uncertainty for unobserved molecule and material classes. This work highlights the potential of lightweight UQ methods in improving the robustness of GNN-based materials modeling and lays the foundation for future integration with active learning strategies.
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。