Towards Unifying Feature Attribution and Counterfactual Explanations: Different Means to the Same End
This work addresses the challenge of improving interpretability for users of ML models by bridging two popular explanation approaches, though it is incremental in nature.
The paper tackles the problem of unifying feature attribution and counterfactual explanations in machine learning by interpreting them through an actual causality framework, showing that these methods often disagree on feature importance and that top features from attribution methods are frequently neither necessary nor sufficient for predictions, as confirmed on benchmark datasets like Adult-Income, LendingClub, and German-Credit.
Feature attributions and counterfactual explanations are popular approaches to explain a ML model. The former assigns an importance score to each input feature, while the latter provides input examples with minimal changes to alter the model's predictions. To unify these approaches, we provide an interpretation based on the actual causality framework and present two key results in terms of their use. First, we present a method to generate feature attribution explanations from a set of counterfactual examples. These feature attributions convey how important a feature is to changing the classification outcome of a model, especially on whether a subset of features is necessary and/or sufficient for that change, which attribution-based methods are unable to provide. Second, we show how counterfactual examples can be used to evaluate the goodness of an attribution-based explanation in terms of its necessity and sufficiency. As a result, we highlight the complementarity of these two approaches. Our evaluation on three benchmark datasets - Adult-Income, LendingClub, and German-Credit - confirms the complementarity. Feature attribution methods like LIME and SHAP and counterfactual explanation methods like Wachter et al. and DiCE often do not agree on feature importance rankings. In addition, by restricting the features that can be modified for generating counterfactual examples, we find that the top-k features from LIME or SHAP are often neither necessary nor sufficient explanations of a model's prediction. Finally, we present a case study of different explanation methods on a real-world hospital triage problem