Esders Malte, Schnake Thomas, Lederer Jonas, Kabylda Adil, Montavon Grégoire, Tkatchenko Alexandre, Müller Klaus-Robert
BIFOLD─Berlin Institute for the Foundations of Learning and Data, 10587 Berlin, Germany.
Machine Learning Group, Berlin Institute of Technology, 10587 Berlin, Germany.
J Chem Theory Comput. 2025 Jan 28;21(2):714-729. doi: 10.1021/acs.jctc.4c01424. Epub 2025 Jan 10.
While machine learning (ML) models have been able to achieve unprecedented accuracies across various prediction tasks in quantum chemistry, it is now apparent that accuracy on a test set alone is not a guarantee for robust chemical modeling such as stable molecular dynamics (MD). To go beyond accuracy, we use explainable artificial intelligence (XAI) techniques to develop a general analysis framework for atomic interactions and apply it to the SchNet and PaiNN neural network models. We compare these interactions with a set of fundamental chemical principles to understand how well the models have learned the underlying physicochemical concepts from the data. We focus on the strength of the interactions for different atomic species, how predictions for intensive and extensive quantum molecular properties are made, and analyze the decay and many-body nature of the interactions with interatomic distance. Models that deviate too far from known physical principles produce unstable MD trajectories, even when they have very high energy and force prediction accuracy. We also suggest further improvements to the ML architectures to better account for the polynomial decay of atomic interactions.
虽然机器学习（ML）模型在量子化学的各种预测任务中已经能够实现前所未有的准确性，但现在很明显，仅在测试集上的准确性并不能保证进行稳健的化学建模，如稳定的分子动力学（MD）。为了超越准确性，我们使用可解释人工智能（XAI）技术来开发一个用于原子相互作用的通用分析框架，并将其应用于SchNet和PaiNN神经网络模型。我们将这些相互作用与一组基本化学原理进行比较，以了解模型从数据中学到基础物理化学概念的程度。我们关注不同原子种类相互作用的强度、如何对强度和广度量子分子性质进行预测，并分析相互作用随原子间距离的衰减和多体性质。偏离已知物理原理太远的模型会产生不稳定的MD轨迹，即使它们具有非常高的能量和力预测准确性。我们还建议对ML架构进行进一步改进，以更好地考虑原子相互作用的多项式衰减。
