Feature Reconstruction Aided Federated Learning for Image Semantic Communication

TL;DR

This paper introduces FedSFR, a federated learning algorithm with semantic feature reconstruction, which improves the stability and effectiveness of image transmission in semantic communication by efficient feature transmission and convergence guarantees.

Contribution

The paper proposes FedSFR, a novel federated learning method that incorporates semantic feature reconstruction to stabilize training and enhance image transmission quality.

Findings

Significantly improved stability and effectiveness in FL-based image transmission.

Efficient communication by transmitting smaller feature vectors.

Mathematically validated convergence rate.

Abstract

Research in semantic communication has garnered considerable attention, particularly in the area of image transmission, where joint source-channel coding (JSCC)-based neural network (NN) modules are frequently employed. However, these systems often experience performance degradation over time due to an outdated knowledge base, highlighting the need for periodic updates. To address this challenge in the context of training JSCC modules for image transmission, we propose a federated learning (FL) algorithm with semantic feature reconstruction (FR), named FedSFR. This algorithm more efficiently utilizes the available communication capacity by allowing some of the selected FL participants to transmit smaller feature vectors instead of local update information. Unlike conventional FL methods, our approach integrates FR at the parameter server (PS), stabilizing training and enhancing image transmission quality. Experimental results demonstrate that the proposed scheme significantly enhances both the stability and effectiveness of the FL process compared to other algorithms. Furthermore, we mathematically derive the convergence rate to validate the improved performance.