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

TL;DR

This paper introduces a quantization-assisted Gaussian differential privacy mechanism to improve convergence, privacy, and fairness in wireless personalized federated learning, addressing communication and privacy challenges.

Contribution

It proposes a novel privacy mechanism and an optimal scheduling strategy for WPFL that enhances fairness and performance under communication constraints.

Findings

Achieves up to 87.08% accuracy improvement

Reduces maximum test loss by 16.21%

Increases fairness (Jain's index) by 38.37%

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.