Federated Learning (FL) is a machine learning technique that enables multiple entities to collaboratively learn a shared model without exchanging their local data. Over the past decade, FL systems have achieved substantial progress, scaling to millions of devices across various learning domains while offering meaningful differential privacy (DP) guarantees. Production systems from organizations like Google, Apple, and Meta demonstrate the real-world applicability of FL. However, key challenges remain, including verifying server-side DP guarantees and coordinating training across heterogeneous devices, limiting broader adoption. Additionally, emerging trends such as large (multi-modal) models and blurred lines between training, inference, and personalization challenge traditional FL frameworks. In response, we propose a redefined FL framework that prioritizes privacy principles rather than rigid definitions. We also chart a path forward by leveraging trusted execution environments and open-source ecosystems to address these challenges and facilitate future advancements in FL.

翻译：联邦学习（Federated Learning, FL）是一种机器学习技术，它允许多个参与方在不交换本地数据的情况下协作训练一个共享模型。过去十年间，联邦学习系统取得了显著进展，已能扩展到不同学习领域的数百万台设备，同时提供有意义的差分隐私（Differential Privacy, DP）保障。来自谷歌、苹果和Meta等组织的生产系统证明了联邦学习在实际应用中的可行性。然而，关键挑战依然存在，包括验证服务器端的差分隐私保证以及在异构设备间协调训练，这限制了其更广泛的采用。此外，大型（多模态）模型的出现，以及训练、推理与个性化之间界限的模糊化等新兴趋势，对传统的联邦学习框架构成了挑战。为此，我们提出一个重新定义的联邦学习框架，该框架优先考虑隐私原则而非僵化的定义。我们还规划了一条前进路径，通过利用可信执行环境和开源生态系统来应对这些挑战，并促进联邦学习未来的发展。