A Comprehensive Taxonomy for Explainable Artificial Intelligence: A Systematic Survey of Surveys on Methods and Concepts
release_4c4zjb6hbbdbxiiw43qtvr3qhq
by
Gesina Schwalbe, Bettina Finzel
2021
Abstract
In the meantime, a wide variety of terminologies, motivations, approaches and
evaluation criteria have been developed within the research field of
explainable artificial intelligence (XAI). With the amount of XAI methods
vastly growing, a taxonomy of methods is needed by researchers as well as
practitioners: To grasp the breadth of the topic, compare methods, and to
select the right XAI method based on traits required by a specific use-case
context. In the literature many taxonomies for XAI methods of varying level of
detail and depth can be found. While they often have a different focus, they
also exhibit many points of overlap. This paper unifies these efforts, and
provides a taxonomy of XAI methods that is complete with respect to notions
present in the current state-of-research. In a structured literature analysis
and meta-study we identified and reviewed more than 50 of the most cited and
current surveys on XAI methods, metrics, and method traits. After summarizing
them in a survey of surveys, we merge terminologies and concepts of the
articles into a unified structured taxonomy. Single concepts therein are
illustrated by in total more than 50 diverse selected example methods, which we
categorize accordingly. The taxonomy may serve both beginners, researchers, and
practitioners as a reference and wide-ranging overview on XAI method traits and
aspects. Hence, it provides foundations for targeted, use-case-oriented, and
context-sensitive future research.
In text/plain
format
Archived Content
There are no accessible files associated with this release. You could check other releases for this work for an accessible version.
Know of a fulltext copy of on the public web? Submit a URL and we will archive it
2105.07190v2
access all versions, variants, and formats of this works (eg, pre-prints)