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.
Yixuan Chen, Zhouxiang Zhao, Wei Xu et al.· 0 citations
Deep learning-based semantic communication has demonstrated superior efficiency in wireless image transmission. However, traditional reactive schemes often suffer from outdated Channel State Information (CSI) in highly dynamic multi-UAV environments, leading to severe latency and utility degradation. To address this challenge, we propose the Predictive and Adaptive Semantic Communication (PASC) framework. PASC integrates a GRU-based predictor to anticipate channel evolution, enabling the proactive adjustment of compression rates by dynamically calibrating attention-weight thresholds. Furthermore, a deadline-aware deep reinforcement learning (DRL) algorithm is proposed to jointly assign sub-channels, allocate bandwidth, and adjust power based on predictive states, thereby preventing resource monopolization. Simulation results confirm that PASC achieves a 58.8% improvement in average Quality of Experience (QoE) compared to non-predictive baselines in low-SNR regimes. Crucially, the framework demonstrates formidable robustness to imperfect CSI, strictly bounding end-to-end latency and maintaining high semantic fidelity even in the presence of extreme prediction noise.
