首个在真实场景下有理论保证的私密联邦学习框架。
First Provable Guarantees for Practical Private FL: Beyond Restrictive Assumptions
- 结合局部更新与部分客户端参与，支持实际部署。
- 在标准假设下实现收敛性与差分隐私双重保证。
- 适合注重隐私保护的工业级联邦学习应用。
联邦学习（FL）允许在去中心化数据上协同训练。差分隐私（DP）对FL至关重要，但现有私密方法常依赖不切实际的假设（如梯度有界或数据异质性），限制了实际应用。现有放宽假设的工作通常忽略实际FL特征，如多轮本地更新和部分客户端参与。本文提出Fed-α-NormEC，首个在标准假设下提供可证明收敛性和差分隐私保障的私密联邦学习框架，同时完全支持多轮本地更新、独立的服务器与客户端步长，以及关键的局部客户端参与机制，该机制对真实部署至关重要且有助于隐私放大。理论分析得到在私密深度学习任务上的实验验证。
原文摘要 · Abstract (English)
Federated Learning (FL) enables collaborative training on decentralized data. Differential privacy (DP) is crucial for FL, but current private methods often rely on unrealistic assumptions (e.g., bounded gradients or heterogeneity), hindering practical application. Existing works that relax these assumptions typically neglect practical FL features, including multiple local updates and partial client participation. We introduce Fed-$α$-NormEC, the first differentially private FL framework providing provable convergence and DP guarantees under standard assumptions while fully supporting these practical features. Fed-$α$-NormE integrates local updates (full and incremental gradient steps), separate server and client stepsizes, and, crucially, partial client participation, which is essential for real-world deployment and vital for privacy amplification. Our theoretical guarantees are corroborated by experiments on private deep learning tasks.
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。