Adaptive role assignment improves federated semantic image communication
Adaptive Role Assignment and Controlled Feature Reconstruction for Federated Image Semantic Communication
Machine Learning
Summary
Semantic communication lets devices share important data features instead of raw data to save bandwidth. The authors propose a new system called ARC-FedSC that smartly assigns roles to devices and controls how image features are reconstructed to fit network limits. Their method learns from each device's past contributions and current network conditions to decide the best role for it, while aligning how image features get combined as the model updates. Tests on image data with changing network quality show ARC-FedSC works better than other methods, giving clearer reconstructed images and making better use of devices.
What this means in practice
- •For mobile network operators: Optimize communication efficiency in cellular networks by adaptive device role management for collaborative image model training under bandwidth limits.
- •For edge ai developers: Improve federated learning deployments by integrating uplink condition-aware role assignment and feature reconstruction control to enhance image semantic communication.
Authors
Yuxuan Chen, Jiao Bie, Hang Qi, Jingjin Wu
Abstract
Hybrid federated semantic communication enables user equipment (UEs) to contribute model updates or semantic features under a shared training framework. However, heterogeneous role costs and the interaction between model aggregation and feature reconstruction (FR) remain key challenges in practical radio access network (RAN) deployment. To address these issues, we propose ARC-FedSC, a RAN-aware framework that coordinates UE role assignment and server-side controlled FR under a fixed communication budget. Within ARC-FedSC, RAN Aware Role-Bandit learns the historical contribution of UEs in different roles together with current uplink conditions, while Temporal Consistency Alignment (TCA) regulates FR according to recent model aggregation directions. Experiments on CIFAR-10 with time-varying RAN channels show that ARC-FedSC outperforms baselines across all five tested role configurations in the later training stage, with the best configurations achieving about 24.17 dB average PSNR over the last 20 rounds. Component level results further show that Role-Bandit maintains an average rolling UE coverage of 85.3%, compared with about 65.7% for baseline, while TCA reduces the probability of harmful FR events from 0.245 to 0.093, corresponding to a 62.0% reduction. Ablation and sensitivity studies further support the effectiveness and robustness of the proposed design.