Debiasing surgeon: fantastic weights and how to find them

arXiv:2403.14200v1 Announce Type: new
Abstract: Nowadays an ever-growing concerning phenomenon, the emergence of algorithmic biases that can lead to unfair models, emerges. Several debiasing approaches have been proposed in the realm of deep learning, employing more or less sophisticated approaches to discourage these models from massively employing these biases. However, a question emerges: is this extra complexity really necessary? Is a vanilla-trained model already embodying some ``unbiased sub-networks'' that can be used in isolation and propose a solution without relying …

abstract arxiv biases cs.ai cs.cv cs.cy cs.lg deep learning emergence however them type