GLANCE: Global Actions in a Nutshell for Counterfactual Explainability

no code implementations • 29 May 2024 • Ioannis Emiris, Dimitris Fotakis, Giorgos Giannopoulos, Dimitrios Gunopulos, Loukas Kavouras, Kleopatra Markou, Eleni Psaroudaki, Dimitrios Rontogiannis, Dimitris Sacharidis, Nikolaos Theologitis, Dimitrios Tomaras, Konstantinos Tsopelas

Counterfactual explanations have emerged as an important tool to understand, debug, and audit complex machine learning models.

counterfactual

FALE: Fairness-Aware ALE Plots for Auditing Bias in Subgroups

no code implementations • 29 Apr 2024 • Giorgos Giannopoulos, Dimitris Sacharidis, Nikolas Theologitis, Loukas Kavouras, Ioannis Emiris

In this work we focus on the latter aspects; we propose an explainability method tailored to identifying potential bias in subgroups and visualizing the findings in a user friendly manner to end users.

Attribute Fairness