arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2303.10797physics.comp-phcond-mat.mtrl-sci
收藏

大型GNN原子模型中超越独立误差假设

Beyond Independent Error Assumptions in Large GNN Atomistic Models

Janghoon Ock, Tian Tian, John Kitchin, Zachary Ulissi

AI总结:

针对GNN原子模型在吸附能相对差异预测中准确性不确定的问题,通过分析Open Catalyst 2020-Dense数据集的约4.83亿对能量差异,发现GNN存在可通过减法降低的相关误差,引入SECR指标后证实其在化学相似子组中误差降低达77%,可媲美DFT的误差抵消效果。

摘要:

确定吸附能相对差异的实际应用十分广泛,例如识别最优催化剂、计算反应能以及确定催化表面上的最低吸附能。尽管密度泛函理论(DFT)可通过系统误差抵消有效计算相对值,但图神经网络(GNNs)在这方面的准确性仍不确定。为研究该问题,我们使用Open Catalyst 2020-Dense数据集,分析了DFT和GNNs预测的约4.83亿对能量差异。分析显示,GNNs存在相关误差,可通过减法降低,这对GNN预测中的朴素独立误差假设提出挑战,并能实现更精确的能量差异预测。为评估化学相似对中的误差抵消程度,我们引入新指标——子组误差抵消比(SECR)。研究发现,最先进的GNN模型在这些子组中可实现高达77%的误差降低,与DFT观测到的误差抵消水平相当。这种显著的误差抵消使GNNs能获得比单个吸附能预测更高的准确性,而单个吸附能预测可能因随机误差传播而放大误差。

英文摘要:

The practical applications of determining the relative difference in adsorption energies are extensive, such as identifying optimal catalysts, calculating reaction energies, and determining the lowest adsorption energy on a catalytic surface. Although Density Functional Theory (DFT) can effectively calculate relative values through systematic error cancellation, the accuracy of Graph Neural Networks (GNNs) in this regard remains uncertain. To investigate this issue, we analyzed approximately 483 million pairs of energy differences predicted by DFT and GNNs using the Open Catalyst 2020 - Dense dataset. Our analysis revealed that GNNs exhibit a correlated error that can be reduced through subtraction, thereby challenging the naive independent error assumption in GNN predictions and leading to more precise energy difference predictions. To assess the magnitude of error cancellation in chemically similar pairs, we introduced a new metric, the subgroup error cancellation ratio (SECR). Our findings suggest that state-of-the-art GNN models can achieve error reduction up to 77% in these subgroups, comparable to the level of error cancellation observed with DFT. This significant error cancellation allows GNNs to achieve higher accuracy than individual adsorption energy predictions, which can otherwise suffer from amplified error due to random error propagation.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑