Hello! I'm Clément Henin, a French civil servant (IPEF) currently working as a PhD student at Inria.
My PhD project, "Explainability of Algorithms", is supervised by Daniel Le Métayer and Claude Castelluccia and is part of the PRIVATICS team work.
My research deals with explainable AI, mainly applied to automatic decision system. I currently work on three research topics:
- Interactive explanations
- Challenges and justifications of automatic decisions
- Application to the French cardiac graft allocation algorithmic system (with Agence de la de Biomédecine)
Publications
Workshop XAI IJCAI 2019 (workshop paper): Clément Henin, Daniel Le Métayer.
Towards a Generic Framework for Black-box Explanation Methods (
pdf )
Workshop DeceptECAI 2020 (workshop paper): Clément Henin, Daniel Le Métayer.
Towards a framework for challenging ML-based decisions (to appear in Springer CCIS,
pdf)
2020 IEEE International Conference on Big Data (Big Data) (pp. 3667-3676) (workshop paper): Clément Henin, Daniel Le Métayer.
A Generic Framework for Black-box Explanations (
editor,
pdf )
2021 Pattern Recognition. ICPR International Workshops and Challenges (workshop paper): Clément Henin, Daniel Le Métayer.
A Multi-layered Approach for Tailored Black-Box Explanations (
editor,
pdf)
Réseaux, 2021/1 (N° 225), p. 187-213 : Clément Henin.
Confier une décision vitale à une machine (
editor)
AI and Ethics (Springer): Clément Henin, Daniel Le Métayer.
A Framework to Contest and Justify Algorithmic Decisions
(editor, pdf)
AI and Society (Springer): Clément Henin, Daniel Le Métayer.
Beyond explainability: justifiability and contestability of algorithmic decision systems. (editor, pdf)
Communications
Workshop XAI IJCAI 2019 (Macao):
Towards a Generic Framework for Black-box Explanation Methods (August 2019)
Workshop DATA (Montreal):
Generic Framework for Interactive Black-box Explanations (September 2019)
Interdisciplinary Workshop on Social Responsability of Algorithm 2019 (Paris Dauphine):
Interactive Black-box explanations (December 2019)
Atelier-débat "Histoire(s) d'algorithmes publics". Etalab, DINUM (December 2019)
Colloque Politiques de la numérisation. Transnum (Sorbonne Université). (February 2020)
International Workshop on Deceptive AI DeceptECAI ECAI2020 (online):
A framework to challenge and justify decisions based on machine learning algorithms. (August 2020)
International Workshop on Fair and Interpretable Learning Algorithms IEEE 2020 (online):
A Generic Framework for Black-box Explanations (Decembre 2020)
Teaching
Travaux dirigés "Machine Learning" du module MALAP à l'École des Ponts ParisTech
Contact
clement.henin@inria.fr