Federated learning (FL) refers to a distributed machine learning framework involving learning from several decentralized edge clients without sharing local dataset. This distributed strategy prevents data leakage and enables on-device training as it updates the global model based on the local model updates. Despite offering several advantages, including data privacy and scalability, FL poses challenges such as statistical and system heterogeneity of data in federated networks, communication bottlenecks, privacy and security issues. This survey contains a systematic summarization of previous work, studies, and experiments on FL and presents a list of possibilities for FL across a range of applications and use cases. Other than that, various challenges of implementing FL and promising directions revolving around the corresponding challenges are provided.

翻译：联邦学习（FL）是指一种分布式机器学习框架，通过在不共享本地数据集的情况下，从多个分散的边缘客户端进行学习。这种分布式策略通过基于本地模型更新来优化全局模型，从而防止数据泄露并支持设备端训练。尽管联邦学习具有数据隐私和可扩展性等多项优势，但它也面临诸多挑战，包括联邦网络中数据的统计异构性与系统异构性、通信瓶颈以及隐私与安全问题。本综述系统总结了联邦学习的现有工作、研究和实验，并列举了联邦学习在各类应用场景中的潜在可能性。此外，本文还探讨了实施联邦学习所面临的各种挑战，以及围绕这些挑战提出的有前景的研究方向。