arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.13451cs.LGcs.DCeess.SP
收藏

抗噪声且资源高效的基于ADMM的联邦学习

Noise-Robust and Resource-Efficient ADMM-based Federated Learning

Department of Electronic Systems, Norwegian University of Science and Technology(挪威科学技术大学电子系统系);Department of Information and Communications Engineering, Aalto University(阿alto大学信息与通信工程系);Commonwealth Scientific and Industrial Research Organisation(共同科学与工业研究组织);SDU Applied AI and Data Science, The Maersk Mc-Kinney Moller Institute, Faculty of Engineering, University of Southern Denmark(南部丹麦大学应用人工智能与数据科学,马士基麦金尼莫勒研究所,工程学院)

Ehsan Lari, Reza Arablouei, Vinay Chakravarthi Gogineni, Stefan Werner

AI总结:

本文提出了一种抗噪声且资源高效的联邦学习算法,通过改进ADMM方法,提高模型鲁棒性和通信效率。

摘要:

联邦学习(FL)利用客户端-服务器通信在去中心化数据上训练全局模型。然而,通信噪声或错误可能会损害模型准确性。为了解决这个问题,我们提出了一种新的FL算法,该算法在增强对通信噪声的鲁棒性的同时也减少了通信负载。我们通过求解加权最小二乘(WLS)回归问题作为示例来推导所提出的算法。我们首先将WLS回归框架为一个分布式凸优化问题,在联邦网络上使用随机调度以提高通信效率。然后,我们应用交替方向乘子法(ADMM)来迭代求解这个问题。为了抵消累积通信噪声的不利影响,我们引入了一个关键修改,通过消除对偶变量并实现新的本地模型更新。这种微妙但有效的改变使每个参与客户端使用一个噪声全局模型更新而不是两个,从而提高对加性通信噪声的鲁棒性。此外,我们还引入了另一个修改,使客户端即使在未被服务器选择时也能继续本地更新,从而带来显著的性能提升。我们的理论分析证实了我们的算法在均值和均方意义下在每次迭代中即使服务器通过有噪声的链路随机选择客户端时也能收敛。数值结果验证了我们所提出算法的有效性,并证实了我们的理论发现。

英文摘要:

Federated learning (FL) leverages client-server communications to train global models on decentralized data. However, communication noise or errors can impair model accuracy. To address this problem, we propose a novel FL algorithm that enhances robustness against communication noise while also reducing communication load. We derive the proposed algorithm through solving the weighted least-squares (WLS) regression problem as an illustrative example. We first frame WLS regression as a distributed convex optimization problem over a federated network employing random scheduling for improved communication efficiency. We then apply the alternating direction method of multipliers (ADMM) to iteratively solve this problem. To counteract the detrimental effects of cumulative communication noise, we introduce a key modification by eliminating the dual variable and implementing a new local model update at each participating client. This subtle yet effective change results in using a single noisy global model update at each client instead of two, improving robustness against additive communication noise. Furthermore, we incorporate another modification enabling clients to continue local updates even when not selected by the server, leading to substantial performance improvements. Our theoretical analysis confirms the convergence of our algorithm in both mean and the mean-square senses, even when the server communicates with a random subset of clients over noisy links at each iteration. Numerical results validate the effectiveness of our proposed algorithm and corroborate our theoretical findings.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑