Séminaire de Probabilités et Statistique
Monday 02 February 2026 à 13:45 - UM, campus Triolet, bâtiment 9, salle 109 (1er étage)
Charlotte Laclau (Télécom Paris)
Fair Classifiers via Transferable Representations
Group fairness is a central research topic in text classification, where reaching fair treatment between sensitive groups (e.g., women and men) remains an open challenge. In this talk, I will present an approach that extends the use of the Wasserstein Independence measure for learning unbiased neural text classifiers. Given the challenge of distinguishing fair from unfair information in a text encoder, we draw inspiration from adversarial training by inducing Wasserstein independence between representations learned for the target label and those for a sensitive attribute. We further show that domain adaptation can be efficiently leveraged to remove the need for access to the sensitive attributes in the dataset at training time. I will present theoretical and empirical evidence of the validity of this approach.
Séminaire en salle 109, également retransmis sur zoom : https://umontpellier-fr.zoom.us/j/7156708132