Julien Ferry
University of Toulouse
10 Papers
12 Citations
Julien Ferry is an academic researcher from University of Toulouse. The author has contributed to research in topics: Computer science & Interpretability. The author has an hindex of 1, co-authored 2 publications. Previous affiliations of Julien Ferry include Laboratory for Analysis and Architecture of Systems.
Chat about Author
Papers
•Posted Content
Learning Fair Rule Lists
TL;DR: The empirical evaluation of FairCORELS on real-world datasets demonstrates that it outperforms state-of-the-art fair classification techniques that are interpretable by design while being competitive with non-interpretable ones.
14
FairCORELS, an Open-Source Library for Learning Fair Rule Lists
Ulrich Aïvodji,Julien Ferry,Sébastien Gambs,Marie-José Huguet,Mohamed Siala +4 more
- 26 Oct 2021
TL;DR: FairCORELS as mentioned in this paper is an open-source Python module for building fair rule lists, which supports six statistical fairness metrics, proposes several exploration parameters and leverages on the fairness constraints to prune the search space efficiently.
6
Learning Optimal Fair Scoring Systems for Multi-Class Classification
Julien Ferry,M. Huguet +1 more
- 01 Oct 2022
TL;DR: In this article , the authors use Mixed-Integer Linear Programming (MILP) techniques to produce inherently interpretable scoring systems under sparsity and fairness constraints, for the general multi-class classification setup.
6
Probabilistic Dataset Reconstruction from Interpretable Models
Julien Ferry,Ulrich Aivodji,Sébastien Gambs,M-J Huguet,Mohamed Siala +4 more
TL;DR: This paper proposes of a novel framework generalizing these probabilistic reconstructions in the sense that it can handle other forms of interpretable models and more generic types of knowledge, and demonstrates that under realistic assumptions regarding theinterpretable models' structure, the uncertainty of the reconstruction can be computed efficiently.
Leveraging Integer Linear Programming to Learn Optimal Fair Rule Lists
Ulrich Aïvodji,Julien Ferry,Sébastien Gambs,M. Huguet,Mohamed,Siala +5 more
- 01 Jan 2022
TL;DR: In this article , the authors investigate and improve on a state-of-the-art exact learning algorithm, called CORELS, which learns rule lists that are certifiably optimal in terms of accuracy and sparsity.