SPADE-DFL：通过无导数线性化ADMM实现通信高效的去中心化联邦学习
SPADE-DFL: Communication-Efficient Decentralized Federated Learning via Derivative-Free Linearized ADMM
查看机构详情
- Southeast University（东南大学）
- Jiangsu Province Scientific Research Center for Applied Mathematics（江苏省应用数学科学研究中心）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
提出SPADE-DFL，一种基于无导数线性化ADMM的去中心化联邦学习方法，通过控制局部更新不一致实现通信高效，在非凸目标下达到T^{-1/3}收敛界，并支持私有训练，实验显示更高准确率。
中文摘要 AI 辅助
减少无导数去中心化学习中的通信需要控制多次局部更新累积的不一致。本文提出了SPADE-DFL，一种原始-对偶方法，允许邻居交换之间的局部函数值更新次数随计算预算增长，同时保持非私有收敛阶数。在均匀查询矩界下，对于光滑非凸目标，所规定的非私有调度实现了时间平均平稳性和共识界为$\mathcal{O}(T^{-1/3})$，仅需$\Theta(T^{2/3})$轮通信，其中$T$是每个客户端的局部更新次数。对于私有训练，累积的数据相关增量与图校正隔离，允许每个客户端每轮一个受保护状态生成所有传出消息。我们证明了完整交互记录的客户端级差分隐私，并量化了有限时间范围内的优化误差。在四个分类任务上的实验表明，SPADE-DFL比现有去中心化学习方法实现了更高的平均测试准确率。
英文摘要
Reducing communication in derivative-free decentralized learning requires controlling the disagreement accumulated over multiple local updates. This paper develops SPADE-DFL, a primal--dual method that allows the number of local function-value updates between neighbor exchanges to grow with the computation budget while preserving the nonprivate convergence order. For smooth nonconvex objectives under uniform query-moment bounds, the prescribed nonprivate schedule achieves a time-averaged stationarity and consensus bound of $\mathcal{O}(T^{-1/3})$ using only $Θ(T^{2/3})$ communication rounds, where $T$ is the number of local updates per client. For private training, the accumulated data-dependent increment is isolated from the graph correction, allowing one protected state per client and round to generate all outgoing messages. We prove client-level differential privacy for the full interactive transcript and quantify the resulting optimization error over a finite horizon. Experiments on four classification tasks show that SPADE-DFL achieves higher mean test accuracy than existing decentralized learning methods.
