Federated Learning is a framework that jointly trains a model with complete knowledge on a remotely placed centralized server, but without the requirement of accessing the data stored in distributed machines. Some work assumes that the data generated from edge devices are identically and independently sampled from a common population distribution. However, such ideal sampling may not be realistic in many contexts. Also, models based on intrinsic agency, such as active sampling schemes, may lead to highly biased sampling. So an imminent question is how robust Federated Learning is to biased sampling? In this work¹ , we experimentally investigate two such scenarios. First, we study a centralized classifier aggregated from a collection of local classifiers trained with data having categorical heterogeneity. Second, we study a classifier aggregated from a collection of local classifiers trained by data through active sampling at the edge. We present evidence in both scenarios that Federated Learning is robust to data heterogeneity when local training iterations and communication frequency are appropriately chosen.

联合学习是一个框架，可在远程集中式服务器上联合训练具有完整知识的模型，但无需访问存储在分布式计算机中的数据。一些工作假设从边缘设备生成的数据是从公共总体分布中相同且独立地采样的。但是，这种理想的采样在许多情况下可能并不现实。此外，基于内在代理的模型（例如主动抽样方案）可能会导致高度偏向的抽样。因此，迫在眉睫的问题是联合学习对有偏抽样的鲁棒性如何？在这项工作¹，我们通过实验研究了两种此类情况。首先，我们研究一个集中的分类器，该分类器是由经过训练的具有分类异质性数据的本地分类器集合聚合而成的。第二，我们研究边缘分类器，该分类器是由数据经过训练的局部分类器集合聚合而成的。在这两种情况下，我们目前的证据表明，联合学习是强大的数据异质性时，当地的培训迭代和通信频率选择适当。