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

TL;DR

This paper develops an explainable message passing neural network with attention mechanisms to predict CO2 adsorption in MOFs, aiming to identify key substructures influencing the prediction for climate change mitigation.

Contribution

It introduces a soft attention mechanism into MPNNs to provide interpretability and identify relevant substructures in MOFs for CO2 adsorption prediction.

Findings

Attention mechanisms highlight important MOF substructures.

Sparse attention mechanisms improve interpretability.

Model achieves accurate CO2 adsorption predictions.

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.