Explaining Deep Learning Models with Constrained Adversarial Examples
This addresses the need for actionable explanations in real-world applications, though it appears incremental as it builds on existing counterfactual and adversarial methods.
The paper tackles the problem of explainability in deep learning by introducing Constrained Adversarial Examples (CADEX), a method for generating counterfactual explanations that show how to achieve different outcomes, incorporating business constraints like categorical attributes and range constraints.
Machine learning algorithms generally suffer from a problem of explainability. Given a classification result from a model, it is typically hard to determine what caused the decision to be made, and to give an informative explanation. We explore a new method of generating counterfactual explanations, which instead of explaining why a particular classification was made explain how a different outcome can be achieved. This gives the recipients of the explanation a better way to understand the outcome, and provides an actionable suggestion. We show that the introduced method of Constrained Adversarial Examples (CADEX) can be used in real world applications, and yields explanations which incorporate business or domain constraints such as handling categorical attributes and range constraints.