arXiv 2506.024222025-06-03cs.DCcs.LG

增强无线个性化联邦学习的收敛性、隐私性与公平性：量化辅助的最小-最大公平调度

Enhancing Convergence, Privacy and Fairness for Wireless Personalized Federated Learning: Quantization-Assisted Min-Max Fair Scheduling

School of Information and Communication Engineering, Beijing University of Posts and Telecommunications（信息与通信工程学院，北京邮电大学）；School of Computing, Macquarie University（计算学院，麦考瑞大学）；Department of Broadband Communication, Peng Cheng Laboratory（宽带通信部，鹏城实验室）；China Telecom, Sichuan Branch（中国电信四川分公司）

Xiyu Zhao, Qimei Cui, Ziqiang Du, Weicai Li, Xi Yu, Wei Ni, Ji Zhang, Xiaofeng Tao, Ping Zhang

DOI：: 10.1109/TMC.2025.3566421

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文针对无线个性化联邦学习中的隐私与公平性问题，提出量化辅助高斯差分隐私机制，并通过最小化收敛上界设计最小-最大公平调度策略，实验表明其在准确率、最大测试损失和公平性上显著优于其他方法。

摘要：

个性化联邦学习（PFL）通过执行联邦学习（FL）来指导个性化学习（PL），提供了一种平衡个性化与泛化能力的解决方案。然而，无线个性化联邦学习（WPFL）中出现的隐私问题很少受到关注。PL模型的性能公平性是WPFL中由通信瓶颈引起的另一个挑战。本文利用量化误差来增强WPFL的隐私性，并提出了一种新颖的量化辅助高斯差分隐私（DP）机制。我们通过考虑该机制（即量化误差和高斯DP噪声）以及不完美通信信道对WPFL中FL的影响，分析了个性化PL模型的收敛上界。通过最小化这些上界中的最大值，我们设计了一种最优传输调度策略，该策略为具有OFDMA接口的WPFL带来了最小-最大公平性。实现这一目标的方法是揭示该问题的嵌套结构，将其解耦为依次求解的子问题，分别用于客户端选择、信道分配和功率控制，以及学习率和PL-FL加权系数。实验验证了我们的分析，并证明我们的方法在准确率、参与客户端的最大测试损失和公平性（Jain指数）方面分别显著优于其他调度策略87.08%、16.21%和38.37%。

英文摘要：

Personalized federated learning (PFL) offers a solution to balancing personalization and generalization by conducting federated learning (FL) to guide personalized learning (PL). Little attention has been given to wireless PFL (WPFL), where privacy concerns arise. Performance fairness of PL models is another challenge resulting from communication bottlenecks in WPFL. This paper exploits quantization errors to enhance the privacy of WPFL and proposes a novel quantization-assisted Gaussian differential privacy (DP) mechanism. We analyze the convergence upper bounds of individual PL models by considering the impact of the mechanism (i.e., quantization errors and Gaussian DP noises) and imperfect communication channels on the FL of WPFL. By minimizing the maximum of the bounds, we design an optimal transmission scheduling strategy that yields min-max fairness for WPFL with OFDMA interfaces. This is achieved by revealing the nested structure of this problem to decouple it into subproblems solved sequentially for the client selection, channel allocation, and power control, and for the learning rates and PL-FL weighting coefficients. Experiments validate our analysis and demonstrate that our approach substantially outperforms alternative scheduling strategies by 87.08%, 16.21%, and 38.37% in accuracy, the maximum test loss of participating clients, and fairness (Jain's index), respectively.

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。