FSSC: Federated Learning of Transformer Neural Networks for Semantic Image Communication

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yan, Yuna, Zhang, Xin, Li, Lixin, Lin, Wensheng, Li, Rui, Cheng, Wenchi, Han, Zhu
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909274982055936
author Yan, Yuna
Zhang, Xin
Li, Lixin
Lin, Wensheng
Li, Rui
Cheng, Wenchi
Han, Zhu
author_facet Yan, Yuna
Zhang, Xin
Li, Lixin
Lin, Wensheng
Li, Rui
Cheng, Wenchi
Han, Zhu
contents In this paper, we address the problem of image semantic communication in a multi-user deployment scenario and propose a federated learning (FL) strategy for a Swin Transformer-based semantic communication system (FSSC). Firstly, we demonstrate that the adoption of a Swin Transformer for joint source-channel coding (JSCC) effectively extracts semantic information in the communication system. Next, the FL framework is introduced to collaboratively learn a global model by aggregating local model parameters, rather than directly sharing clients' data. This approach enhances user privacy protection and reduces the workload on the server or mobile edge. Simulation evaluations indicate that our method outperforms the typical JSCC algorithm and traditional separate-based communication algorithms. Particularly after integrating local semantics, the global aggregation model has further increased the Peak Signal-to-Noise Ratio (PSNR) by more than 2dB, thoroughly proving the effectiveness of our algorithm.
format Preprint
id arxiv_https___arxiv_org_abs_2407_21507
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle FSSC: Federated Learning of Transformer Neural Networks for Semantic Image Communication
Yan, Yuna
Zhang, Xin
Li, Lixin
Lin, Wensheng
Li, Rui
Cheng, Wenchi
Han, Zhu
Artificial Intelligence
Machine Learning
Image and Video Processing
In this paper, we address the problem of image semantic communication in a multi-user deployment scenario and propose a federated learning (FL) strategy for a Swin Transformer-based semantic communication system (FSSC). Firstly, we demonstrate that the adoption of a Swin Transformer for joint source-channel coding (JSCC) effectively extracts semantic information in the communication system. Next, the FL framework is introduced to collaboratively learn a global model by aggregating local model parameters, rather than directly sharing clients' data. This approach enhances user privacy protection and reduces the workload on the server or mobile edge. Simulation evaluations indicate that our method outperforms the typical JSCC algorithm and traditional separate-based communication algorithms. Particularly after integrating local semantics, the global aggregation model has further increased the Peak Signal-to-Noise Ratio (PSNR) by more than 2dB, thoroughly proving the effectiveness of our algorithm.
title FSSC: Federated Learning of Transformer Neural Networks for Semantic Image Communication
topic Artificial Intelligence
Machine Learning
Image and Video Processing
url https://arxiv.org/abs/2407.21507