Recently, lots of algorithms have been proposed for learning a fair classifier from decentralized data. However, many theoretical and algorithmic questions remain open. First, is federated learning necessary, i.e., can we simply train locally fair classifiers and aggregate them? In this work, we first propose a new theoretical framework, with which we demonstrate that federated learning can strictly boost model fairness compared with such non-federated algorithms. We then theoretically and empirically show that the performance tradeoff of FedAvg-based fair learning algorithms is strictly worse than that of a fair classifier trained on centralized data. To bridge this gap, we propose FedFB, a private fair learning algorithm on decentralized data. The key idea is to modify the FedAvg protocol so that it can effectively mimic the centralized fair learning. Our experimental results show that FedFB significantly outperforms existing approaches, sometimes matching the performance of the centrally trained model.
翻译:最近,许多算法被推荐用于从分散的数据中学习公平分类。然而,许多理论和算法问题仍然有待解决。首先,联合会的学习是必要的,也就是说,我们能否仅仅培训当地公平的分类人员并加以汇总?在这项工作中,我们首先提出一个新的理论框架,通过这个框架,我们证明联合会的学习能够严格地促进模型公平性,而这种非集中的算法则则与此相比。我们随后在理论上和经验上表明,基于FedAvg的公平学习算法的绩效权衡比受过集中数据培训的公平分类人员差得多。为了弥补这一差距,我们建议FDFB,这是关于分散数据的私人公平学习算法。关键的想法是修改FDAvg协议,以便它能够有效地模拟集中的公平学习。我们的实验结果表明,FDFB大大超越了现有方法,有时与经过集中培训的模式的绩效匹配。