Towards explainable message passing networks for predicting carbon dioxide adsorption in metal-organic frameworks

Abstract

Metal-organic framework (MOFs) are nanoporous materials that could be used to capture carbon dioxide from the exhaust gas of fossil fuel power plants to mitigate climate change. In this work, we design and train a message passing neural network (MPNN) to predict simulated CO${}_2$ adsorption in MOFs. Towards providing insights into what substructures of the MOFs are important for the prediction, we introduce a soft attention mechanism into the readout function that quantifies the contributions of the node representations towards the graph representations. We investigate different mechanisms for sparse attention to ensure only the most relevant substructures are identified.

accepted paper at the Machine Learning for Molecules Workshop - NeurIPS 2020 conference

References in corpus (12)

• Neural Message Passing for Quantum Chemistry
• Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties
• Molecular Graph Convolutions: Moving Beyond Fingerprints
• Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals
• Universal Fragment Descriptors for Predicting Electronic Properties of Inorganic Crystals
• Attention is not Explanation
• Learning Deep Generative Models of Graphs
• Gated Graph Sequence Neural Networks
• Machine Learning for Scent: Learning Generalizable Perceptual Representations of Small Molecules
• Neural Message Passing with Edge Updates for Predicting Properties of Molecules and Materials
• Understanding the Message Passing in Graph Neural Networks via Power Iteration Clustering
• Graph Neural Networks Including Sparse Interpretability