FedAlign：面向非独立同分布联邦学习的差分隐私分布对齐
FedAlign: Differentially Private Distribution Alignment for Non-IID Federated Learning
为视觉模型在跨设备联邦训练中提供一种可复用的隐私保护分布对齐手段：客户端上传加噪的统计矩、服务器聚合推断全局分布并回传指导本地对齐，可直接嵌入现有的联邦视觉训练流程以缓解 Non-IID 导致的收敛慢与精度下降。
原文依据 Clients upload perturbed distribution statistics, which the server aggregates to infer global distribution characteristics and guide local alignment
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论联邦学习（FL）能够在不共享原始数据的前提下实现协作式模型训练，但客户端数据往往是非独立同分布的（Non-IID），这通常会减慢收敛速度并降低全局性能。与此同时，隐私保护也是联邦学习中的一个关键问题。为解决这两个问题，我们提出 FedAlign，一个通过客户端侧统计矩对齐来对齐本地数据分布的差分隐私框架。客户端上传经过扰动的分布统计量，服务器对这些统计量进行聚合以推断全局分布特征并指导本地对齐，从而减小客户端之间的差异。实验与理论分析表明，FedAlign 在非独立同分布设置下加快了收敛并提升了准确率，同时保持了严格的隐私保证。
英文原文摘要 828 字符
Federated Learning (FL) enables collaborative model training without sharing raw data, but client data are often Non-Independent and Identically Distributed (Non-IID), which often slow convergence and degrade global performance. Meanwhile, privacy preservation is also a critical concern in FL. To address these two issues, we propose FedAlign, a differentially private framework that aligns local data distributions via client-side statistical moment alignment. Clients upload perturbed distribution statistics, which the server aggregates to infer global distribution characteristics and guide local alignment, thereby reducing inter-client discrepancies. Experiments and theoretical analysis show that FedAlign accelerates convergence and improves accuracy under Non-IID settings while preserving rigorous privacy guarantees.