no code implementations • 18 Oct 2022 • Virginie Do, Elvis Dohmatob, Matteo Pirotta, Alessandro Lazaric, Nicolas Usunier
We consider Contextual Bandits with Concave Rewards (CBCR), a multi-objective bandit problem where the desired trade-off between the rewards is defined by a known concave objective function, and the reward vector depends on an observed stochastic context.
no code implementations • 13 Sep 2022 • Nicolas Usunier, Virginie Do, Elvis Dohmatob
In this paper, we propose the first efficient online algorithm to optimize concave objective functions in the space of rankings which applies to every concave and smooth objective function, such as the ones found for fairness of exposure.
no code implementations • 14 May 2022 • Thierry Kirst, Olivia Tambou, Virginie Do, Alexis Tsoukiàs
The contextualization will focus on the legal systems of the United States on the one hand and Europe on the other.
no code implementations • 2 Apr 2022 • Virginie Do, Nicolas Usunier
Depending on these weights, GGFs minimize the Gini index of item exposure to promote equality between items, or focus on the performance on specific quantiles of least satisfied users.
no code implementations • 14 Feb 2022 • Virginie Do, Matthieu Hervouin, Jérôme Lang, Piotr Skowron
Assume $k$ candidates need to be selected.
no code implementations • NeurIPS 2021 • Virginie Do, Sam Corbett-Davies, Jamal Atif, Nicolas Usunier
Our experiments also show that it increases the utility of the worse-off at lower costs in terms of overall utility.
no code implementations • 19 May 2021 • Virginie Do, Jamal Atif, Jérôme Lang, Nicolas Usunier
Citizens' assemblies need to represent subpopulations according to their proportions in the general population.
2 code implementations • ICCV 2021 • Maxime Kayser, Oana-Maria Camburu, Leonard Salewski, Cornelius Emde, Virginie Do, Zeynep Akata, Thomas Lukasiewicz
e-ViL is a benchmark for explainable vision-language tasks that establishes a unified evaluation framework and provides the first comprehensive comparison of existing approaches that generate NLEs for VL tasks.
no code implementations • 29 Apr 2021 • Virginie Do, Sam Corbett-Davies, Jamal Atif, Nicolas Usunier
We propose to audit for envy-freeness, a more granular criterion aligned with individual preferences: every user should prefer their recommendations to those of other users.
3 code implementations • 7 Apr 2020 • Virginie Do, Oana-Maria Camburu, Zeynep Akata, Thomas Lukasiewicz
The recently proposed SNLI-VE corpus for recognising visual-textual entailment is a large, real-world dataset for fine-grained multimodal reasoning.