Federated Learning (FL) is a promising distributed learning mechanism which still faces two major challenges, namely privacy breaches and system efficiency. In this work, we reconceptualize the FL system from the perspective of network information theory, and formulate an original FL communication framework, FedNC, which is inspired by Network Coding (NC). The main idea of FedNC is mixing the information of the local models by making random linear combinations of the original packets, before uploading for further aggregation. Due to the benefits of the coding scheme, both theoretical and experimental analysis indicate that FedNC improves the performance of traditional FL in several important ways, including security, throughput, and robustness. To the best of our knowledge, this is the first framework where NC is introduced in FL. As FL continues to evolve within practical network frameworks, more applications and variants can be further designed based on FedNC.

翻译：联邦学习（FL）是一种具有前景的分布式学习机制，但仍面临两大主要挑战，即隐私泄露与系统效率。本文从网络信息论角度重新诠释FL系统，并受网络编码（NC）启发，构建了原始FL通信框架FedNC。FedNC的核心思想是在上传本地模型进行聚合前，通过对原始数据包进行随机线性组合来混合本地模型信息。由于编码方案的优势，理论与实验分析均表明，FedNC在安全性、吞吐量和鲁棒性等多个关键方面提升了传统FL的性能。据我们所知，这是首个将NC引入FL的框架。随着FL在实际网络框架中的持续演进，基于FedNC可进一步设计更多应用与变体。