联合学习是一个很有吸引力的概念，它可以在保持数据私密性的同时进行神经网络的分布式训练。随着FL框架的产业化，我们发现了几个阻碍其成功部署的问题，例如非i.i.d数据的存在、不相交的类、跨数据集的信号多模式。在这项工作中，我们提出了一种新的方法来解决这些问题，该方法不仅(1)在服务器上(例如，在传统的FL中)聚合通用模型参数(例如，一组通用的任务神经网络层)，而且(2)保留一组特定于每个客户端的参数(例如，一组特定于任务的神经网络层)。我们在传统使用的公共基准(如Femnist)和专有收集数据集(如流量分类)上验证我们的方法。结果表明了该方法的优越性，在极端情况下具有明显优势。

原文题目：Heterogeneous Data-Aware Federated Learning

原文：Federated learning (FL) is an appealing concept to perform distributed training of Neural Networks (NN) while keeping data private. With the industrialization of the FL framework, we identify several problems hampering its successful deployment, such as presence of non i.i.d data, disjoint classes, signal multimodality across datasets. In this work, we address these problems by proposing a novel method that not only (1) aggregates generic model parameters (e.g. a common set of task generic NN layers) on server (e.g. in traditional FL), but also (2) keeps a set of parameters (e.g, a set of task specific NN layer) specific to each client. We validate our method on the traditionally used public benchmarks (e.g., Femnist) as well as on our proprietary collected dataset (i.e., traffic classification). Results show the benefit of our method, with significant advantage on extreme cases.

原文作者：Lixuan Yang, Cedric Beliard, Dario Rossi

原文地址：https://arxiv.org/abs/2011.06393