In federated learning, model personalization can be a very effective strategy to deal with heterogeneous training data across clients. We introduce WAFFLE (Weighted Averaging For Federated LEarning), a personalized collaborative machine learning algorithm that leverages stochastic control variates for faster convergence. WAFFLE uses the Euclidean distance between clients' updates to weigh their individual contributions and thus minimize the personalized model loss on the specific agent of interest. Through a series of experiments, we compare our new approach to two recent personalized federated learning methods--Weight Erosion and APFL--as well as two general FL methods--Federated Averaging and SCAFFOLD. Performance is evaluated using two categories of non-identical client data distributions--concept shift and label skew--on two image data sets (MNIST and CIFAR10). Our experiments demonstrate the comparative effectiveness of WAFFLE, as it achieves or improves accuracy with faster convergence.

翻译：在联合学习中,模型个性化可以成为处理不同客户不同培训数据的一个非常有效的战略。我们引入了WAFFLE(对联邦列车的加权自动转换),这是一种个性化的协作机器学习算法,利用随机控制变异来加快趋同。WAFFLE使用客户最新资料之间的Euclidean距离来权衡其个人贡献,从而尽量减少特定利益主体的个人化模型损失。我们通过一系列实验,将我们的新办法与最近两种个性化的联邦化学习方法(Weight Erosion和APFL-as)以及两种通用FL方法(FL方法-联邦列车和SCAFFFOLD)进行了比较,利用两类非同客户数据分配-概念转换和两个图像数据集(MNIST和CIFAR10)的标签Skew-on-boat。我们的实验显示了WAFFLE的比较效力,因为它实现或提高精度,与更快的趋同。