Feature Attribution As Feature Selection

Abstract

Feature attribution methods identify "relevant" features as an explanation of a complex machine learning model. Several feature attribution methods have been proposed; however, only a few studies have attempted to define the "relevance" of each feature mathematically. In this study, we formalize the feature attribution problem as a feature selection problem. In our proposed formalization, there arise two possible definitions of relevance. We name the feature attribution problems based on these two relevances as Exclusive Feature Selection (EFS) and Inclusive Feature Selection (IFS). We show that several existing feature attribution methods can be interpreted as approximation algorithms for EFS and IFS. Moreover, through exhaustive experiments, we show that IFS is better suited as the formalization for the feature attribution problem than EFS.

Tasks

Reproductions