AN AGNOSTIC APPROACH TO FEDERATED LEARNING WITH CLASS IMBALANCE

         本地分布和全局分布有可能是不一致的——本地的少数类有可能是全局的多数类。出于隐私考虑，又不能暴露本地分布。

        To overcome the aforementioned challenges, we propose a constrained learning formulation to handle the class imbalance issue in FL while accounting for both heterogeneity and privacy. In brief, we impose constraints on the standard FL formulation so that the empirical loss on every client should not overly exceed the average empirical loss. Such constraints are shown to force the classifier to account for all classes equally and hence mitigate the detrimental effect of class imbalance, under a type of heterogeneous data configuration that captures the mismatch between the local and global imbalance.

        这篇论文的核心就是他不管分布信息，以一种Agnostic的方式来面对Class Imbalance in FL。

论文提出： 

（是不是有点像Fedprox？）

接下来通过拉格朗日乘子来求解，数学看不懂。

论文的实验设置有些新奇：

 他的 Imbalance Ratio是自己定义的，而不是像大家约定的那样

 

 论文的理论性比较强，但我感觉效果上应该不太行的。换个设置估计就不行了。但是并不妨碍中了顶会。