1 code implementation • 27 Oct 2023 • Vincent Grari, Thibault Laugel, Tatsunori Hashimoto, Sylvain Lamprier, Marcin Detyniecki
In the field of algorithmic fairness, significant attention has been put on group fairness criteria, such as Demographic Parity and Equalized Odds.
no code implementations • 10 May 2023 • Thibault Laugel, Adulam Jeyasothy, Marie-Jeanne Lesot, Christophe Marsala, Marcin Detyniecki
In the field of Explainable Artificial Intelligence (XAI), counterfactual examples explain to a user the predictions of a trained decision model by indicating the modifications to be made to the instance so as to change its associated prediction.
1 code implementation • 14 Feb 2023 • Natasa Krco, Thibault Laugel, Jean-Michel Loubes, Marcin Detyniecki
With comparable performances in fairness and accuracy, are the different bias mitigation approaches impacting a similar number of individuals?
no code implementations • 25 Apr 2022 • Adulam Jeyasothy, Thibault Laugel, Marie-Jeanne Lesot, Christophe Marsala, Marcin Detyniecki
In the field of eXplainable Artificial Intelligence (XAI), post-hoc interpretability methods aim at explaining to a user the predictions of a trained decision model.
no code implementations • 9 Jul 2021 • Tom Vermeire, Thibault Laugel, Xavier Renard, David Martens, Marcin Detyniecki
Explainability is becoming an important requirement for organizations that make use of automated decision-making due to regulatory initiatives and a shift in public awareness.
no code implementations • 9 Jul 2021 • Rafael Poyiadzi, Xavier Renard, Thibault Laugel, Raul Santos-Rodriguez, Marcin Detyniecki
This paper analyses the fundamental ingredients behind surrogate explanations to provide a better understanding of their inner workings.
no code implementations • 10 Jun 2021 • Rafael Poyiadzi, Xavier Renard, Thibault Laugel, Raul Santos-Rodriguez, Marcin Detyniecki
In this work we review the similarities and differences amongst multiple methods, with a particular focus on what information they extract from the model, as this has large impact on the output: the explanation.
no code implementations • 12 Apr 2021 • Xavier Renard, Thibault Laugel, Marcin Detyniecki
This paper proposes to address this question by analyzing the prediction discrepancies in a pool of best-performing models trained on the same data.
1 code implementation • 8 Nov 2019 • Vincent Ballet, Xavier Renard, Jonathan Aigrain, Thibault Laugel, Pascal Frossard, Marcin Detyniecki
Security of machine learning models is a concern as they may face adversarial attacks for unwarranted advantageous decisions.
1 code implementation • 22 Jul 2019 • Thibault Laugel, Marie-Jeanne Lesot, Christophe Marsala, Xavier Renard, Marcin Detyniecki
Post-hoc interpretability approaches have been proven to be powerful tools to generate explanations for the predictions made by a trained black-box model.
no code implementations • 11 Jun 2019 • Thibault Laugel, Marie-Jeanne Lesot, Christophe Marsala, Marcin Detyniecki
Counterfactual post-hoc interpretability approaches have been proven to be useful tools to generate explanations for the predictions of a trained blackbox classifier.
no code implementations • 7 Sep 2018 • Xavier Renard, Thibault Laugel, Marie-Jeanne Lesot, Christophe Marsala, Marcin Detyniecki
Machine learning models are increasingly used in the industry to make decisions such as credit insurance approval.
1 code implementation • 19 Jun 2018 • Thibault Laugel, Xavier Renard, Marie-Jeanne Lesot, Christophe Marsala, Marcin Detyniecki
Local surrogate models, to approximate the local decision boundary of a black-box classifier, constitute one approach to generate explanations for the rationale behind an individual prediction made by the back-box.
6 code implementations • 22 Dec 2017 • Thibault Laugel, Marie-Jeanne Lesot, Christophe Marsala, Xavier Renard, Marcin Detyniecki
In the context of post-hoc interpretability, this paper addresses the task of explaining the prediction of a classifier, considering the case where no information is available, neither on the classifier itself, nor on the processed data (neither the training nor the test data).