approved
GLocalX - Explaining in a Local to Global setting

GLocalX is a model-agnostic Local to Global explanation algorithm. Given a set of local explanations expressed in the form of decision rules, and a black-box model to explain, GLocalX refines the local explanations into global ones, accounting both for their fidelity and complexity.

Tags
Data and Resources
To access the resources you must log in
  • Github pageGitHub

    Github of the GLocalX algorithm.

    The resource: 'Github page' is not accessible as guest user. You must login to access it!
  • Journal article itemHTML

    Link to the Journal item

    The resource: 'Journal article item' is not accessible as guest user. You must login to access it!
Additional Info
Field Value
Accessibility Both
AccessibilityMode Download
Availability On-Line
Basic rights Download
CreationDate 2021-01-01
Creator Setzu, Mattia, mattia.setzu@phd.unipi.it, orcid.org/0000-0001-8351-9999
External Identifier https://doi.org/10.1016/j.artint.2021.103457
Field/Scope of use Any use
Github https://github.com/msetzu/glocalx
Group Social Impact of AI and explainable ML
Journal item https://ckan-sobigdata.d4science.org/dataset/glocalx-from_local_to_global_explanations_of_black_box_ai_models
Owner Setzu, Mattia, mattia.setzu@phd.unipi.it, orcid.org/0000-0001-8351-9999
ProgrammingLanguage Python3.8
Sublicense rights No
Territory of use World Wide
Thematic Cluster Other
system:type Method
Management Info
Field Value
Author Setzu Mattia
Maintainer Setzu Mattia
Version 1
Last Updated 8 September 2023, 14:51 (CEST)
Created 20 May 2021, 12:40 (CEST)