Federated learning (FL) has emerged as a secure paradigm for collaborative training among clients. Without data centralization, FL allows clients to share local information in a privacy-preserving manner. This approach has gained considerable attention, promoting numerous surveys to summarize the related works. However, the majority of these surveys concentrate on FL methods that share model parameters during the training process, while overlooking the possibility of sharing local information in other forms. In this paper, we present a systematic survey from a new perspective of what to share in FL, with an emphasis on the model utility, privacy leakage, and communication efficiency. First, we present a new taxonomy of FL methods in terms of three sharing methods, which respectively share model, synthetic data, and knowledge. Second, we analyze the vulnerability of different sharing methods to privacy attacks and review the defense mechanisms. Third, we conduct extensive experiments to compare the learning performance and communication overhead of various sharing methods in FL. Besides, we assess the potential privacy leakage through model inversion and membership inference attacks, while comparing the effectiveness of various defense approaches. Finally, we identify future research directions and conclude the survey.

翻译：联邦学习（FL）已成为一种安全的客户端协作训练范式。无需数据集中化，FL允许客户端以保护隐私的方式共享本地信息。该方法已获得广泛关注，催生了大量总结相关工作的综述。然而，这些综述多数聚焦于训练过程中共享模型参数的FL方法，忽视以其他形式共享本地信息的可能性。本文从FL中共享内容的新视角进行系统综述，重点关注意模型效用、隐私泄露与通信效率。首先，我们依据共享模型、合成数据与知识这三种共享方式提出FL方法的新分类体系。其次，分析不同共享方式对隐私攻击的脆弱性并综述防御机制。第三，开展大量实验比较FL中多种共享方式的学习性能与通信开销。同时，通过模型反转攻击与成员推断攻击评估潜在隐私泄露，并对比多种防御方法的有效性。最后，指出未来研究方向并总结全文。