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

2025-06-03

IEEE Transactions on Mobile Computing

AI Summary

To address three key challenges in wireless personalized federated learning (WPFL)—poor convergence due to communication constraints, privacy leakage risks, and unfair personalized performance—this paper proposes: (1) a quantization-error-enhanced Gaussian differential privacy mechanism, the first to achieve synergistic gains between quantization efficiency and privacy preservation; (2) a min-max fair scheduling framework explicitly designed to minimize the worst-case convergence bound, thereby guaranteeing robust performance for the most disadvantaged client; and (3) a joint optimization strategy leveraging problem nesting to co-design OFDMA resource allocation, client selection, power control, learning rate, and personalization weights. Theoretical analysis and extensive experiments demonstrate that the proposed method improves test accuracy, worst-client test loss, and Jain’s fairness index by 87.08%, 16.21%, and 38.37%, respectively, significantly outperforming state-of-the-art approaches.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Search and Optimization: Learning to Search
• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Responsible Web: Data and user privacy-enhancing technologies for the Web
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing

Abstract

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.

Problem

• Enhancing privacy in wireless personalized federated learning using quantization-assisted DP
• Improving fairness among personalized models in communication-constrained WPFL
• Optimizing transmission scheduling for min-max fairness in OFDMA-based WPFL

Innovation

• Quantization-assisted Gaussian DP mechanism
• Min-max fair scheduling strategy
• Nested problem decoupling for optimization