Fed-PELAD: Communication-Efficient Federated Learning for Massive MIMO CSI Feedback with Personalized Encoders and a LoRA-Adapted Shared Decoder

TL;DR

Fed-PELAD introduces a federated learning framework with personalized encoders and a LoRA-adapted shared decoder to reduce communication costs and improve CSI feedback accuracy in massive MIMO systems, addressing heterogeneity and privacy.

Contribution

The paper presents a novel federated learning approach with personalized encoders and LoRA-based shared decoder for efficient CSI feedback in massive MIMO, reducing communication overhead and enhancing performance.

Findings

Requires only 42.97% of uplink communication compared to traditional methods.

Achieves a 1.2 dB improvement in CSI feedback accuracy.

Demonstrates robustness under heterogeneous channel conditions.

Abstract

This paper addresses the critical challenges of communication overhead, data heterogeneity, and privacy in deep learning for channel state information (CSI) feedback in massive MIMO systems. To this end, we propose Fed-PELAD, a novel federated learning framework that incorporates personalized encoders and a LoRA-adapted shared decoder. Specifically, personalized encoders are trained locally on each user equipment (UE) to capture device-specific channel characteristics, while a shared decoder is updated globally via the coordination of the base station (BS) by using Low-Rank Adaptation (LoRA). This design ensures that only compact LoRA adapter parameters instead of full model updates are transmitted for aggregation. To further enhance convergence stability, we introduce an alternating freezing strategy with calibrated learning-rate ratio during LoRA aggregation. Extensive simulations on 3GPP-standard channel models demonstrate that Fed-PELAD requires only 42.97\% of the uplink communication cost compared to conventional methods while achieving a performance gain of 1.2 dB in CSI feedback accuracy under heterogeneous conditions.