PhD graduated
Team : LFI
Localisation : Campus Pierre et Marie CurieSorbonne Université - LIP6 Boîte courrier 169 Couloir 26-00, Étage 5, Bureau 516 4 place Jussieu 75252 PARIS CEDEX 05 FRANCE Tel: +33 1 44 27 87 26, Thibault.Laugel (at) nulllip6.fr http://webia.lip6.fr/~laugel/
Supervision : Christophe MARSALA Co-supervision : LESOT Marie-Jeanne, DETYNIECKI Marcin
Local Post-hoc Interpretability for Black-box Classifiers
This thesis focuses on the field of XAI (eXplainable AI), and more particularly local post-hoc interpretability paradigm, that is to say the generation of explanations for a single prediction of a trained classifier. In particular, we study a fully agnostic context, meaning that the explanation is generated without using any knowledge about the classifier (treated as a black-box) nor the data used to train it. In this thesis, we identify several issues that can arise in this context and that may be harmful for interpretability. We propose to study each of these issues and propose novel criteria and approaches to detect and characterize them. The three issues we focus on are: the risk of generating explanations that are out of distribution; the risk of generating explanations that cannot be associated to any ground-truth instance; and the risk of generating explanations that are not local enough. These risks are studied through two specific categories of interpretability approaches: counterfactual explanations and local surrogate models.
Defence : 07/03/2020 - 14h00 - Visioconférence Jury members : M. Jamal Atif (rapporteur), Dauphine LAMSADE
M. Marcin Detyniecki (invité, encadrant), AXA
Mme Fosca Giannotti (rapporteur, visioconférence), Université de Pise KDDLab / ISTI-CNR
Mme Marie-Jeanne Lesot (co-directrice), Sorbonne Université LIP6
M. Christophe Marsala (co-directeur), Sorbonne Université LIP6
M. Nicolas Maudet (examinateur), Sorbonne Université LIP6
M. Chris Russell (examinateur), Alan Turing Institute / University of Surrey
Th. Laugel, M.‑J. Lesot, Ch. Marsala, X. Renard, M. Detyniecki : “The Dangers of Post-hoc Interpretability: Unjustified Counterfactual Explanations”, Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, {IJCAI-19}, Macao, Macao, pp. 2801-2807, (International Joint Conferences on Artificial Intelligence Organization) (2019)
X. Renard, Th. Laugel, M.‑J. Lesot, Ch. Marsala, M. Detyniecki : “Detecting Potential Local Adversarial Examples for Human-Interpretable Defense”, Workshop on Recent Advances in Adversarial Learning (Nemesis) of the European Conference on Machine Learning and Principles of Practice of Knowledge Discovery in Databases (ECML-PKDD), Dublin, Ireland (2018)
Th. Laugel, X. Renard, M.‑J. Lesot, Ch. Marsala, M. Detyniecki : “Defining Locality for Surrogates in Post-hoc Interpretablity”, Workshop on Human Interpretability for Machine Learning (WHI) - International Conference on Machine Learning (ICML), Stockholm, Sweden (2018)
Th. Laugel, M.‑J. Lesot, Ch. Marsala, X. Renard, M. Detyniecki : “Comparison-based Inverse Classification for Interpretability in Machine Learning”, 17th International Conference on Information Processing and Management of Uncertainty in Knowledge-Based Systems (IPMU 2018), Information Processing and Management of Uncertainty in Knowledge-Based Systems. Theory and Foundations, Cadix, Spain, pp. 100-111, (Springer Verlag) (2018)
LIP6 » News » PhD students
Local Post-hoc Interpretability for Black-box Classifiers