Analyzing Atomic Interactions in Molecules as Learned by Neural Networks

Abstract

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.

References in corpus (30)

• Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties
• Methods for Interpreting and Understanding Deep Neural Networks
• SchNet - a deep learning architecture for molecules and materials
• Shortcut Learning in Deep Neural Networks
• E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications
• Explaining NonLinear Classification Decisions with Deep Taylor Decomposition
• Machine Learning of Accurate Energy-Conserving Molecular Force Fields
• Machine learning for molecular simulation
• Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical Systems
• SchNetPack: A Deep Learning Toolbox For Atomistic Systems
• Interpretable and Explainable Machine Learning for Materials Science and Chemistry
• Higher-Order Explanations of Graph Neural Networks via Relevant Walks
• Forces are not Enough: Benchmark and Critical Evaluation for Machine Learning Force Fields with Molecular Simulations
• Using Attribution to Decode Dataset Bias in Neural Network Models for Chemistry
• From Clustering to Cluster Explanations via Neural Networks
• Towards Explaining Anomalies: A Deep Taylor Decomposition of One-Class Models
• Strategies for the Construction of Machine-Learning Potentials for Accurate and Efficient Atomic-Scale Simulations
• SchNetPack 2.0: A neural network toolbox for atomistic machine learning
• Explaining and Interpreting LSTMs
• Building and Interpreting Deep Similarity Models
• MACE-OFF: Transferable Short Range Machine Learning Force Fields for Organic Molecules
• Accurate Computation of Quantum Excited States with Neural Networks
• A Hitchhiker's Guide to Geometric GNNs for 3D Atomic Systems
• Robustness of Local Predictions in Atomistic Machine Learning Models
• Towards Symbolic XAI -- Explanation Through Human Understandable Logical Relationships Between Features
• Peering inside the black box: Learning the relevance of many-body functions in Neural Network potentials
• An improved penalty-based excited-state variational Monte Carlo approach with deep-learning ansatzes
• Decoupling Pixel Flipping and Occlusion Strategy for Consistent XAI Benchmarks