FairNeuron: Improving Deep Neural Network Fairness with Adversary Games on Selective Neurons. (arXiv:2204.02567v1 [cs.LG])

With Deep Neural Network (DNN) being integrated into a growing number of
critical systems with far-reaching impacts on society, there are increasing
concerns on their ethical performance, such as fairness. Unfortunately, model
fairness and accuracy in many cases are contradictory goals to optimize. To
solve this issue, there has been a number of work trying to improve model
fairness by using an adversarial game in model level. This approach introduces
an adversary that evaluates the fairness of a model besides …

arxiv deep neural network fairness games network neural network neurons