FSSC: Federated Learning of Transformer Neural Networks for Semantic Image Communication
This addresses privacy and efficiency in multi-user image communication, though it appears incremental by combining existing techniques.
The paper tackles image semantic communication in multi-user scenarios by proposing a federated learning strategy for a Swin Transformer-based system, which outperforms typical joint source-channel coding and traditional algorithms, increasing Peak Signal-to-Noise Ratio by over 2dB after integrating local semantics.
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.