Federated learning improves semantic communication over shared wireless channels
Federated Learning for Semantic Communications over Multiple Access Channels
Information TheoryDistributed, Parallel, and Cluster ComputingMachine LearningNetworking and Internet Architecture
Summary
Wireless devices sending meaningful information often need to train their systems separately, which takes a lot of time and data. This paper shows a way for many devices to learn together by sending their information at the same time over a shared wireless channel. The method helps devices with less data learn from those with more, making the system faster and more accurate even when data is uneven among devices. Tests using image data showed the approach keeps accuracy high and reduces the time needed for training.
What this means in practice
- •For wireless network engineers: Design wireless systems that efficiently support multiple devices sending learned semantic data simultaneously to reduce training time and channel use.
- •For edge ai developers: Develop edge intelligence solutions where devices with limited data can leverage federated learning to improve semantic communications under varying channel conditions.
Authors
Yalin E. Sagduyu, Tugba Erpek, Yi Shi
Abstract
This paper presents a federated learning (FL) framework for semantic communication (SemCom) over the multiple access channel (MAC), where multiple distributed transmitters simultaneously convey semantic information to a common receiver using end-to-end learned semantic representations. Semantic feature extraction, compression, wireless transmission, and semantic inference are jointly optimized through FL-based SemCom. Unlike conventional SemCom systems that train users independently, simultaneous semantic transmissions over the MAC enable concurrent training of multiple transmitters within the same transmission interval, thereby reducing training overhead and channel usage. Federated semantic aggregation is incorporated with shared and personalized encoder components, allowing transmitters with limited local training data to benefit from semantic representations learned from transmitters possessing larger datasets while preserving local adaptation. Evaluated using the CIFAR-10 dataset over fading channels, the proposed approach maintains high semantic inference accuracy under shared wireless access and significantly improves performance under severe data imbalance. In the meantime, simultaneous semantic transmissions can significantly reduce training overhead while preserving robust semantic performance across distributed transmitters with heterogeneous local datasets. These results highlight the potential of combining FL and SemCom to support scalable and communication-efficient edge intelligence in future wireless networks.