Towards a Generic Framework for Black-box Explanation Methods (Extended Version)
Vers un cadre générique pour l’explication en mode boı̂te noire des systèmes de décision algorithmique (version étendue)
Abstract
The main goal of this paper is to define a generic framework for black-box explanation
methods in order to make it easier to compare and classify different approaches. We focus on
two components of this framework, called respectively “Sampling” and “Generation”, which are
characterized formally and used to build a taxonomy of explanation methods. This document gives
details on how this framework can be used to describe black-box explanation methods found in
the literature.
Origin | Files produced by the author(s) |
---|
Loading...