2 papers
cs.LG2023
SANGEA: Scalable and Attributed Network Generation
Valentin Lemaire, Youssef Achenchabe, Lucas Ody +4
The topic of synthetic graph generators (SGGs) has recently received much attention due to the wave of the latest breakthroughs in generative modelling. However, many state-of-the-…
cs.LG2023
A Fair Classifier Embracing Triplet Collapse
A. Martzloff, N. Posocco, Q. Ferré
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 classif…