articleData Mining and Knowledge DiscoveryJun 3, 2023HYBRID OA

Benchmarking and survey of explanation methods for black box models

FBFrancesco BodriaFGFosca GiannottiRGRiccardo GuidottiFNFrancesca NarettoDPDino Pedreschi

Scuola Normale Superiore · University of Pisa · +1 more institution

Indexed incrossref

Abstract

Abstract The rise of sophisticated black-box machine learning models in Artificial Intelligence systems has prompted the need for explanation methods that reveal how these models work in an understandable way to users and decision makers. Unsurprisingly, the state-of-the-art exhibits currently a plethora of explainers providing many different types of explanations. With the aim of providing a compass for researchers and practitioners, this paper proposes a categorization of explanation methods from the perspective of the type of explanation they return, also considering the different input data formats. The paper accounts for the most representative explainers to date, also discussing similarities and…

Citation impact

234
total citations
FWCI
34.79
Percentile
100%
References
190
Citations per year

Authors

6

Topics & keywords

Topics
Keywords
  • Benchmarking
  • Categorization
  • Computer science
  • Perspective (graphical)
  • Repertoire
  • Artificial intelligence
  • Black box
  • Data science
UN Sustainable Development Goals
  • Peace, Justice and strong institutions
No related works found for this paper.

Funding