A New Class of Explanations for Classifiers with Non-Binary Features
This work addresses the need for better interpretability in machine learning for users dealing with classifiers that have non-binary features, representing an incremental advancement.
The paper tackles the problem of explaining classifier decisions by improving necessary and sufficient reasons for non-binary features, resulting in a new class of explanations that relay more information about decisions and classifiers.
Two types of explanations have been receiving increased attention in the literature when analyzing the decisions made by classifiers. The first type explains why a decision was made and is known as a sufficient reason for the decision, also an abductive explanation or a PI-explanation. The second type explains why some other decision was not made and is known as a necessary reason for the decision, also a contrastive or counterfactual explanation. These explanations were defined for classifiers with binary, discrete and, in some cases, continuous features. We show that these explanations can be significantly improved in the presence of non-binary features, leading to a new class of explanations that relay more information about decisions and the underlying classifiers. Necessary and sufficient reasons were also shown to be the prime implicates and implicants of the complete reason for a decision, which can be obtained using a quantification operator. We show that our improved notions of necessary and sufficient reasons are also prime implicates and implicants but for an improved notion of complete reason obtained by a new quantification operator that we also define and study.