6 papers · 1 filter
ACT: Agentic Classification Tree
Vincent Grari, Tim Arni, Thibault Laugel +3
When used in high-stakes settings, AI systems are expected to produce decisions that are transparent, interpretable and auditable, a requirement increasingly expected by regulation…
Why do explanations fail? A typology and discussion on failures in XAI
Clara Bove, Thibault Laugel, Marie-Jeanne Lesot +2
As Machine Learning models achieve unprecedented levels of performance, the XAI domain aims at making these models understandable by presenting end-users with intelligible explanat…
Controlled Model Debiasing through Minimal and Interpretable Updates
Federico Di Gennaro, Thibault Laugel, Vincent Grari +1
Traditional approaches to learning fair machine learning models often require rebuilding models from scratch, typically without considering potentially existing models. In a contex…
Post-processing fairness with minimal changes
Federico Di Gennaro, Thibault Laugel, Vincent Grari +2
In this paper, we introduce a novel post-processing algorithm that is both model-agnostic and does not require the sensitive attribute at test time. In addition, our algorithm is e…
Understanding Prediction Discrepancies in Machine Learning Classifiers
Xavier Renard, Thibault Laugel, Marcin Detyniecki
A multitude of classifiers can be trained on the same data to achieve similar performances during test time, while having learned significantly different classification patterns. T…
When mitigating bias is unfair: multiplicity and arbitrariness in algorithmic group fairness
Natasa Krco, Thibault Laugel, Vincent Grari +2
Most research on fair machine learning has prioritized optimizing criteria such as Demographic Parity and Equalized Odds. Despite these efforts, there remains a limited understandi…