重定义联邦学习框架，强化隐私保护并应对设备异构挑战
Federated Learning in Practice: Reflections and Projections
- 以隐私为核心重构联邦学习，突破传统框架限制
- 支持百万级设备协同训练，实现可验证的差分隐私保障
- 适合关注隐私计算与大规模分布式学习的研究者与工程师
联邦学习（FL）是一种允许多方在不共享本地数据的前提下协同训练共享模型的机器学习技术。过去十年间，FL系统已实现显著进展，覆盖数百万设备，广泛应用于各类学习场景，并提供可验证的差分隐私（DP）保障。谷歌、苹果、Meta等企业的生产系统证实了其实际可行性。然而，服务器端DP验证困难、异构设备训练协调难等问题仍制约其广泛应用。此外，大模型（多模态）兴起及训练、推理与个性化界限模糊，对传统FL框架提出挑战。为此，本文提出以隐私原则为导向的新框架，强调灵活性而非严格定义，并通过可信执行环境与开源生态推动未来演进。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。