论文标题
用分子反事实解释深图网络
Explaining Deep Graph Networks with Molecular Counterfactuals
论文作者
论文摘要
我们提出了一种新的方法，可以在分子属性预测任务（分子解释发生器）的背景下解决深图网络的解释性。我们在具有高结构相似性和不同预测属性的（有效）化合物的形式下为特定预测产生信息的反事实解释。我们讨论了初步结果，该结果表明该模型如何通过关键见解传达非ML专家，以对分子附近的学习模型进行关注。
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.
