Semantic Communication in Dynamic Channel Scenarios: Collaborative Optimization of Dual-Pipeline Joint Source-Channel Coding and Personalized Federated Learning
This work addresses bandwidth and latency issues in communication systems for users in dynamic channel environments, representing an incremental improvement through a hybrid approach.
The paper tackles the challenge of generalizing semantic communication models in complex network scenarios with multiple users by proposing a personalized federated learning framework with dual-pipeline joint source-channel coding, achieving zero optimization gap for non-convex loss functions and validating performance across diverse datasets under varying SNR distributions.
Semantic communication is designed to tackle issues like bandwidth constraints and high latency in communication systems. However, in complex network topologies with multiple users, the enormous combinations of client data and channel state information (CSI) pose significant challenges for existing semantic communication architectures. To improve the generalization ability of semantic communication models in complex scenarios while meeting the personalized needs of each user in their local environments, we propose a novel personalized federated learning framework with dual-pipeline joint source-channel coding based on channel awareness model (PFL-DPJSCCA). Within this framework, we present a method that achieves zero optimization gap for non-convex loss functions. Experiments conducted under varying SNR distributions validate the outstanding performance of our framework across diverse datasets.