Straggler-Resilient Federated Learning over A Hybrid Conventional and Pinching Antenna Network

TL;DR

This paper introduces a hybrid antenna network with a fuzzy logic client classification and a DRL-based optimization to improve communication efficiency and mitigate stragglers in federated learning over wireless networks.

Contribution

It proposes a novel hybrid antenna system combined with a fuzzy classification and DRL optimization for better FL performance.

Findings

Enhanced FL performance with optimized antenna deployment.

Effective mitigation of stragglers through dynamic LoS link establishment.

Improved communication efficiency in NOMA-enabled FL systems.

Abstract

Leveraging pinching antennas in wireless network enabled federated learning (FL) can effectively mitigate the common "straggler" issue in FL by dynamically establishing strong line-of-sight (LoS) links on demand. This letter proposes a hybrid conventional and pinching antenna network (HCPAN) to significantly improve communication efficiency in the non-orthogonal multiple access (NOMA)-enabled FL system. Within this framework, a fuzzy logic-based client classification scheme is first proposed to effectively balance clients' data contributions and communication conditions. Given this classification, we formulate a total time minimization problem to jointly optimize pinching antenna placement and resource allocation. Due to the complexity of variable coupling and non-convexity, a deep reinforcement learning (DRL)-based algorithm is developed to effectively address this problem. Simulation results validate the superiority of the proposed scheme in enhancing FL performance via the optimized deployment of pinching antenna.