Federated Unlearning Over Wireless Networks

2026-08-09

AI Summary

This work addresses the reliability challenges in wireless federated unlearning caused by high communication latency and channel uncertainty. It is the first to incorporate worst-case bounded channel state information errors into system modeling, establishing a joint optimization framework that integrates algorithmic convergence, local computation dynamics, and robust wireless transmission. By leveraging monotonicity and convexity properties, the authors devise a low-complexity iterative algorithm that jointly optimizes bandwidth allocation, transmit power, computation frequency, and local accuracy through a combination of uniform scanning, nested bisection, and golden-section search. The proposed method achieves polynomial time complexity and significantly reduces the total federated unlearning completion time, outperforming existing baseline approaches.

Abstract

To comply with stringent data privacy regulations, federated unlearning (FU) has emerged as a critical paradigm. However, its implementation over wireless networks introduces severe communication latency and reliability challenges due to iterative calibration requirements and physical-layer channel uncertainties. In this paper, we investigate the problem of delay minimization for federated unlearning networks (FUN). Specifically, we establish a comprehensive system model that jointly incorporates the convergence behavior of the FUN algorithm, local device computation dynamics, and a worst-case robust transmission model operating under bounded channel state information (CSI) error. To solve the resulting non-convex joint resource allocation problem, we propose an efficient iterative algorithm. By exploiting the monotonicity and convexity properties of the system constraints, the problem is decomposed via a uniform scan over the local accuracy parameter, within which the optimal delay, bandwidth, power, and computation frequency are determined utilizing nested bisection and golden-section searches. Both theoretical analysis and extensive numerical results demonstrate that the proposed algorithm achieves polynomial complexity and significantly reduces the overall unlearning completion time compared to conventional baseline schemes.

Problem

• Federated Unlearning
• Wireless Networks
• Communication Latency
• Channel Uncertainty
• Delay Minimization

Innovation

• Federated Unlearning
• Wireless Networks
• Resource Allocation
• Robust Transmission
• Delay Minimization