EXPEKCTATION

Papers

2024

Gilles Audemard, Sylvie Coste-Marquis, Pierre Marquis, Mehdi Sabiri, Nicolas Szczepanski.
"Designing an XAI Interface for Tree-Based ML Models". In proceedings of ECAI’24, pp 1075-1082.
pdf   Supplementary material

Gilles Audemard, Jean-Marie Lagniez, Pierre Marquis.
"On the Computation of Contrastive Explanations for Boosted Regression Trees". In proceedings of ECAI’24, pp 1083-1091.
pdf  Supplementary material

Frédéric Koriche, Jean-Marie Lagniez, Stefan Mengel, Chi Tran
"Learning Model Agnostic Explanations via Constraint Programming". In proceedings of ECML/PKDD’24, pp 437-453.
pdf

Jean-Marie Lagniez, Pierre Marquis, Armin Biere.
"Dynamic Blocked Clause Elimination for Projected Model Counting". In proceedings of SAT’24, pp 21:1-21:17.
pdf

Gilles Audemard, Jean-Marie Lagniez, Pierre Marquis, Nicolas Szczepanski.
"PyXAI: An XAI Library for Tree-Based Models". In proceedings of IJCAI’24, pp 8601-8605.
pdf

Gilles Audemard, Jean-Marie Lagniez, Pierre Marquis, Nicolas Szczepanski.
"On the Computation of Example-Based Abductive Explanations for Random Forests". In proceedings of IJCAI’24, pp 3679-3687.
pdf  Supplementary material

Gilles Audemard, Jean-Marie Lagniez, Pierre Marquis, Nicolas Szczepanski.
"Deriving Provably Correct Explanations for Decision Trees: The Impact of Domain Theories". In proceedings of IJCAI’24, pp 3688-3696.
pdf proofs

Jérémie Bottieau, Gilles Audemard, Steve Bellart, Jean-Marie Lagniez, Pierre Marquis, Nicolas Szczepanski, Jean-François Toubeau.
"Logic-Based Explanations of Imbalance Price Forecasts Using Boosted Trees". Electric Power Systems Research, vol. 235, October 2024.
pdf

2023

Sylvie Coste-Marquis, Pierre Marquis.
"Rectifying Binary Classifiers". In proceedings of ECAI'23, pp. 485-492.
pdf

Gilles Audemard, Jean-Marie Lagniez, Pierre Marquis, Nicolas Szczepanski.
"On Contrastive Explanations for Tree-Based Classifiers". In proceedings of ECAI'23, pp. 117-124.
pdf Supplementary material

Gilles Audemard, Jean-Marie Lagniez, Pierre Marquis, Nicolas Szczepanski.
"Computing Abductive Explanations for Boosted Trees". In proceedings of AISTATS'23, pp. 4699-4711.
pdf Supplementary material

Louenas Bounia, Frédéric Koriche.
"Approximating probabilistic explanations via supermodular minimization". In proceedings of UAI’23, pp. 216-225.
pdf   Poster  Supplementary material 

Gilles Audemard, Steve Bellart, Jean-Marie Lagniez, Pierre Marquis.
"Computing Abductive Explanations for Boosted Regression Trees". In proceedings of IJCAI’23, pp. 3432-3441.
pdf   Supplementary material

Alexis de Colnet, Pierre Marquis.
"On Translations between ML Models for XAI Purposes". In proceedings of IJCAI’23, pp. 3158-3166.
pdf

Nicolas Schwind, Katsumi Inoue, Pierre Marquis.
"Editing Boolean Classifiers: A Belief Change Perspective". In proceedings of AAAI’23, pp. 6516-6524.
pdf

Gilles Audemard, Steve Bellart, Louenas Bounia, Frédéric Koriche, Jean-Marie Lagniez, Pierre Marquis.
"Sur les explications abductives préférées pour les arbres de décision et les forêts aléatoires". It is a French version of "On Preferred Abductive Explanations for Decision Trees and Random Forests" (IJCAI'22). In proceedings of EGC'23, pp. 507-514.
pdf

Gilles Audemard, Steve Bellart, Louenas Bounia, Jean-Marie Lagniez, Pierre Marquis, Nicolas Szczepanski.
In French. "PyXAI : calculer en Python des explications pour des modèles d'apprentissage supervisé". In proceedings of EGC'23, pp. 581-588.
pdf

2022

Gilles Audemard, Steve Bellart, Louenas Bounia, Frédéric Koriche, Jean-Marie Lagniez, Pierre Marquis.
"On the Explanatory Power of Boolean Decision Trees". In Data & Knowledge Engineering. Vol 142, 2022.
. This paper is an extended version of "On the Explanatory Power of Decision Trees" (Technical report, 2021). pdf 

Gilles Audemard, Marie Miceli, Jean-Marie Lagniez.
"A New Exact Solver for (Weighted) Max#SAT". In proceedings of SAT'22, pp. 1-20.
pdf

Alexis de Colnet, Pierre Marquis.
"On the Complexity of Enumerating Prime Implicants from Decision-DNNF Circuits". In proceedings of IJCAI'22, pp. 2583-2590.
pdf

Gilles Audemard, Steve Bellart, Louenas Bounia, Frédéric Koriche, Jean-Marie Lagniez, Pierre Marquis.
"On Preferred Abductive Explanations for Decision Trees and Random Forests". In proceedings of IJCAI'22, pp. 643-650.
pdf  video supplementary material

Adnan Darwiche, Pierre Marquis.
"On Quantifying Literals in Boolean Logic and its Applications to Explainable AI (Extended Abstract)". This paper is an extended abstract of the corresponding JAIR paper. In proceedings of IJCAI'22, pp. 5718-5721.
pdf

Gilles Audemard, Steve Bellart, Louenas Bounia, Frédéric Koriche, Jean-Marie Lagniez, Pierre Marquis.
"Trading Complexity for Sparsity in Random Forest Explanations". In proceedings of AAAI'22, pp. 5461-5469.
pdf  video supplementary material

Sylvie Coste-Marquis, Pierre Marquis.
"Rectifying Mono-Label Boolean Classifiers". Technical report, 2022.
pdf   video (keynote lecture at DL-NMR'22)

Gilles Audemard, Steve Bellart, Louenas Bounia, Frédéric Koriche, Jean-Marie Lagniez, Pierre Marquis.
"Les raisons majoritaires : des explications abductives pour les forêts aléatoires". In proceedings of EGC'22, pp. 123-134.
It is a French version of "Trading Complexity for Sparsity in Random Forest Explanations" (AAAI'22).
pdf

Gilles Audemard, Steve Bellart, Louenas Bounia, Frédéric Koriche, Jean-Marie Lagniez, Pierre Marquis.
"Sur le pouvoir explicatif des arbres de décision". In proceedings of EGC'22, pp. 147-158.
It is a French version of of "On the Explanatory Power of Decision Trees" (Technical report, 2021).
pdf

2021

Adnan Darwiche, Pierre Marquis.
"On Quantifying Literals in Boolean Logic and Its Applications to Explainable AI". Journal of Artificial Intelligence Research, 2021, vol 72, pp. 285-328.
pdf   

Gilles Audemard, Steve Bellart, Louenas Bounia, Frédéric Koriche, Jean-Marie Lagniez, Pierre Marquis.
"Trading Complexity for Sparsity in Random Forest Explanations". Technical report, 2021.
pdf Supplementary material

Gilles Audemard, Steve Bellart, Louenas Bounia, Frédéric Koriche, Jean-Marie Lagniez, Pierre Marquis.
"On the Explanatory Power of Decision Trees". Technical report, 2021.
pdf Supplementary material

Gilles Audemard, Steve Bellart, Louenas Bounia, Frédéric Koriche, Jean-Marie Lagniez, Pierre Marquis.
"On the Computational Intelligibility of Boolean Classifiers". In proceedings of KR'21, pp. 74-86.
pdf    video  

Sylvie Coste-Marquis, Pierre Marquis.
"On Belief Change for Multi-Label Classifier Encodings". In proceedings of IJCAI'21, pp. 1829-1836.
pdf    video

2020

Gilles Audemard, Frédéric Koriche, Pierre Marquis.
"On Tractable XAI Queries based on Compiled Representations". In proceedings of KR'20, pp. 838-849.
pdf    video

Sylvie Coste-Marquis, Pierre Marquis.
"From Explanations to Intelligible Explanations". In 1st International Workshop on Explainable Logic-Based Knowledge Representation (XLoKR’20), 2020. (Workshop at KR’20).
pdf    video

Talks

Pierre Marquis.
Open Meeting TAILOR (June 27th 2023).
Trustworthy AI@Artois University: Main Contributions.
video

Pierre Marquis.
In French. Knowledge Representation and Explainability, Cours IA², Paris 2021.
video

Theses

Steve Bellart.
In French. Calcul d'explications formelles pour les modèles d'apprentissage automatique à ensemble d'arbres.. Dec 2023.

Louenas Bounia.
In French. Modèles formels pour l'IA explicable : des explications pour les arbres de décision.. Dec 2023.