论文标题
同上：通过个性化公平，强大的联邦学习
Ditto: Fair and Robust Federated Learning Through Personalization
论文作者
论文摘要
公平和鲁棒性是联合学习系统的两个重要问题。在这项工作中，我们确定对数据和模型中毒攻击和公平性的鲁棒性，以跨设备的性能的统一性来衡量，这是统计上异质性网络的竞争限制。为了解决这些限制，我们建议使用一个简单的一般框架进行个性化联合学习，同上，可以天生地提供公平和鲁棒性的好处，并为其开发可扩展的求解器。从理论上讲，我们分析了同上同时在一系列线性问题上同时实现公平性和鲁棒性的能力。从经验上讲，在一系列联合数据集中，我们表明同上不仅相对于最近的个性化方法，还可以实现竞争性能，而且还可以使相对于最先进的公平或鲁棒的基线提供更准确，健壮和公平的模型。
Fairness and robustness are two important concerns for federated learning systems. In this work, we identify that robustness to data and model poisoning attacks and fairness, measured as the uniformity of performance across devices, are competing constraints in statistically heterogeneous networks. To address these constraints, we propose employing a simple, general framework for personalized federated learning, Ditto, that can inherently provide fairness and robustness benefits, and develop a scalable solver for it. Theoretically, we analyze the ability of Ditto to achieve fairness and robustness simultaneously on a class of linear problems. Empirically, across a suite of federated datasets, we show that Ditto not only achieves competitive performance relative to recent personalization methods, but also enables more accurate, robust, and fair models relative to state-of-the-art fair or robust baselines.
