A Fair Classifier Embracing Triplet Collapse

In this paper, we study the behaviour of the triplet loss and show that it can be exploited to limit the biases created and perpetuated by machine learning models. Our fair classifier uses the collapse of the triplet loss when its margin is greater than the maximum distance between two points in the latent space, in the case of stochastic triplet selection.

Alice Martzloff, Nicolas Posocco, Quentin Ferré, A Fair Classifier Embracing Triplet Collapse, In Proc. of The Conférence sur l’Apprentissage Automatique, July 2023.

Click here to access the paper.