PhD graduated
Team : LFI
Departure date : 02/20/2024

Supervision : Marie-Jeanne LESOT, Christophe MARSALA

Co-supervision : LAUGEL Thibault (AXA)

Interprétabilité des modèles en apprentissage automatique

This thesis belongs to the field of eXplainable AI (XAI). We focus on post-hoc interpretability methods that aim to explain to a user the prediction made for a specific data instance by a trained decision model.
To increase the interpretability of explanations, this thesis studies the integration of user knowledge into these methods, and thus aims to improve the comprehensibility of the explanation by generating personalized explanations adapted to each user. To achieve this, we propose a general formalism that explicitly integrates knowledge via a new criterion in the interpretability objectives. This formalism is then declined for different types of knowledge and different types of explanations, particularly counterfactual examples, leading to the proposal of several algorithms (KICE, Knowledge Integration in Counterfactual Explanation, rKICE for its variant including knowledge expressed by rules and KISM, Knowledge Integration in Surrogate Models).
The issue of aggregating classical quality and knowledge compatibility constraints is also studied, and we propose to use Gödel's integral as an aggregation operator.
Finally, we discuss the difficulty of generating a single explanation adapted to all types of users and the notion of diversity in explanations.

Defence : 02/20/2024

Jury members :

Wassila OUERDANE, Maîtresse de conférences HDR, Centrale Supélec [Rapporteur]
Benjamin QUOST, Maître de conférences HDR, Université de technologie de Compiègne [Rapporteur]
Salem BENFERHAT, Professeur des universités, Université d'Artois
Grégory BOURGUIN, Maître de conférences, Université du littoral Côte d'Opale
Marc PLANTEVIT, Professeur des universités, EPITA
Thibault LAUGEL, Chargé de recherche, AXA
Marie-Jeanne LESOT, Professeure des universités, Sorbonne Université
Christophe MARSALA, Professeur des universités, Sorbonne Université

Departure date : 02/20/2024

2022-2024 Publications