Toward Fairness via Maximum Mean Discrepancy Regularization on Logits Space
This addresses fairness issues in high-risk applications like healthcare and facial recognition, representing an incremental improvement over existing logits space methods.
The authors tackled fairness deficiencies in previous logits space constraint methods by proposing Logits-MMD, a framework that imposes Maximum Mean Discrepancy constraints on output logits. The method outperforms previous approaches and achieves state-of-the-art results on two facial recognition datasets and one animal dataset.
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 on two facial recognition datasets and one animal dataset. Finally, we show experimental results and demonstrate that our debias approach achieves the fairness condition effectively.