Ditto: Fair and Robust Federated Learning Through Personalization
Ditto: Fair and Robust Federated Learning Through Personalization
复制标题
DOI：
--
复制
发表时间：
2020-12
期刊：
影响因子：
--
通讯作者：
Tian Li;Shengyuan Hu;Ahmad Beirami;Virginia Smith
中科院分区：
文献类型：
--
作者：
Tian Li;Shengyuan Hu;Ahmad Beirami;Virginia Smith
公平性和鲁棒性是联邦学习系统的两个重要问题。在这项工作中，我们确定，数据和模型中毒攻击和公平性的鲁棒性，衡量跨设备的性能的均匀性，在统计异构网络的竞争约束。为了解决这些限制，我们建议采用一个简单的，一般的框架，个性化的联邦学习，同上，可以提供内在的公平性和鲁棒性的好处，并开发一个可扩展的solver为it.Theoretically，我们分析的能力，同上实现公平性和鲁棒性同时对一类线性问题。从经验上讲，在一套联合数据集上，我们表明Ditto不仅相对于最近的个性化方法实现了具有竞争力的性能，而且相对于最先进的公平或稳健的基线，还实现了更准确，稳健和公平的模型。
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.