Toward Fairness via Maximum Mean Discrepancy Regularization on Logits Space

arXiv:2402.13061v1 Announce Type: new
Abstract: Fairness has become increasingly pivotal in machine learning for high-risk applications such as machine learning in healthcare and facial recognition. However, we see the deficiency in the previous logits space constraint methods. Therefore, we propose a novel framework, Logits-MMD, that achieves the fairness condition by imposing constraints on output logits with Maximum Mean Discrepancy. Moreover, quantitative analysis and experimental results show that our framework has a better property that outperforms previous methods and achieves state-of-the-art …

abstract applications arxiv become cs.cv facial recognition fairness framework healthcare machine machine learning mean novel pivotal recognition regularization risk space type via