Explaining Deep Graph Networks with Molecular Counterfactuals
arXiv:2011.05134
Abstract
We present a novel approach to tackle explainability of deep graph networks in the context of molecule property prediction tasks, named MEG (Molecular Explanation Generator). We generate informative counterfactual explanations for a specific prediction under the form of (valid) compounds with high structural similarity and different predicted properties. We discuss preliminary results showing how the model can convey non-ML experts with key insights into the learning model focus in the neighborhood of a molecule.
6 pages, 6 figures, accepted at NeurIPS2020 Workshop on Machine Learning for Molecules