Feature Necessity & Relevancy in ML Classifier Explanations
It addresses the need for more rigorous explanations in ML, particularly for applications requiring sensitivity analysis, but is incremental as it builds on existing logic-based abduction frameworks.
This paper tackles the problem of determining whether sensitive features can appear in explanations for ML classifier predictions and whether non-interesting features must appear, by relating these queries to relevancy and necessity in logic-based abduction, and it proves computational complexity results and proposes scalable algorithms for specific classifier families.
Given a machine learning (ML) model and a prediction, explanations can be defined as sets of features which are sufficient for the prediction. In some applications, and besides asking for an explanation, it is also critical to understand whether sensitive features can occur in some explanation, or whether a non-interesting feature must occur in all explanations. This paper starts by relating such queries respectively with the problems of relevancy and necessity in logic-based abduction. The paper then proves membership and hardness results for several families of ML classifiers. Afterwards the paper proposes concrete algorithms for two classes of classifiers. The experimental results confirm the scalability of the proposed algorithms.