用ADMM改进分层联邦学习，提升隐私与收敛速度
Hierarchical Federated ADMM
- 顶层用ADMM协调，底层可选ADMM或梯度下降
- 在有限本地迭代下，底层梯度下降仍表现良好
- 适合注重隐私与通信效率的分布式场景
本文摒弃主流的基于梯度下降的分层联邦学习算法，提出一种基于交替方向乘子法（ADMM）的新框架。该框架在顶层使用ADMM，底层则分别采用ADMM或传统梯度下降方法。实验表明，所提算法在学习收敛性和准确率上优于传统方法，且更具隐私保护性。当本地迭代次数较少时，底层采用梯度下降仍表现稳健；而在更多本地迭代条件下，双层均采用ADMM性能更优。
原文摘要 · Abstract (English)
In this paper, we depart from the widely-used gradient descent-based hierarchical federated learning (FL) algorithms to develop a novel hierarchical FL framework based on the alternating direction method of multipliers (ADMM). Within this framework, we propose two novel FL algorithms, which both use ADMM in the top layer: one that employs ADMM in the lower layer and another that uses the conventional gradient descent-based approach. The proposed framework enhances privacy, and experiments demonstrate the superiority of the proposed algorithms compared to the conventional algorithms in terms of learning convergence and accuracy. Additionally, gradient descent on the lower layer performs well even if the number of local steps is very limited, while ADMM on both layers lead to better performance otherwise.
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。