We consider the problem of achieving fair classification in Federated Learning (FL) under data heterogeneity. Most of the approaches proposed for fair classification require diverse data that represent the different demographic groups involved. In contrast, it is common for each client to own data that represents only a single demographic group. Hence the existing approaches cannot be adopted for fair classification models at the client level. To resolve this challenge, we propose several aggregation techniques. We empirically validate these techniques by comparing the resulting fairness metrics and accuracy on CelebA, UTK, and FairFace datasets.
翻译:我们考虑了在联邦学习联合会(FL)中实现数据差异的公平分类问题,为公平分类而提出的大多数方法都需要代表不同人口群体的不同数据,而每个客户通常只拥有代表单一人口群体的数据,因此无法在客户一级采用公平分类模式。为了解决这一挑战,我们建议采用几种汇总技术。我们通过比较CelebA、UTK和Fair Face数据集的公平度量和准确性,对这些技术进行经验验证。