用相关噪声提升隐私保护下的在线联邦学习性能
Locally Differentially Private Online Federated Learning With Correlated Noise
- 引入时间相关噪声，在保护隐私的同时提升学习效用
- 在$(ε,δ)$-LDP约束下，实现动态环境中的可证明性能保障
- 适用于非独立同分布的流式数据，适合实际部署场景
我们提出一种用于在线联邦学习的局部差分隐私（LDP）算法，采用时间相关的噪声以在保护隐私的同时提升学习效用。针对相关噪声与流式非独立同分布数据带来的局部更新挑战，我们构建了扰动迭代分析方法，有效控制噪声对模型性能的影响。此外，我们证明了对于多类非凸损失函数，本地更新引起的漂移误差可被有效管理。在$(ε,δ)$-LDP预算下，我们建立了动态后悔界，量化了关键参数及动态环境变化强度对学习性能的影响。数值实验验证了该算法的有效性。
原文摘要 · Abstract (English)
We introduce a locally differentially private (LDP) algorithm for online federated learning that employs temporally correlated noise to improve utility while preserving privacy. To address challenges posed by the correlated noise and local updates with streaming non-IID data, we develop a perturbed iterate analysis that controls the impact of the noise on the utility. Moreover, we demonstrate how the drift errors from local updates can be effectively managed for several classes of nonconvex loss functions. Subject to an $(ε,δ)$-LDP budget, we establish a dynamic regret bound that quantifies the impact of key parameters and the intensity of changes in the dynamic environment on the learning performance. Numerical experiments confirm the efficacy of the proposed algorithm.
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。