aiqbench analysis
The paper proposes training several distributed transmitters at once over a shared wireless channel, using federated learning with shared and personalized encoders. Its evaluation on CIFAR-10 over fading channels suggests the approach helps transmitters with little local data, but the results come from a simulated image-classification setup, not a deployed system. Readers interested in edge intelligence and communication-efficient training should watch how the method holds up under realistic channel conditions and data heterogeneity.
Federated Learning for Semantic Communications over Multiple Access Channels
arXiv:2610.37951v1 Announce Type: cross 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.
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.
Information Theory (cs.IT); Distributed, Parallel, and Cluster Computing (cs.DC); Machine Learning (cs.LG); Networking and Internet Architecture (cs.NI); Signal Processing (eess.SP)
arXiv:2610.37951 [cs.IT]
(or arXiv:2610.37951v1 [cs.IT] for this version)
From: Yalin E. Sagduyu [view email] [v1] Tue, 27 Oct 2026 20:36:42 UTC (155 KB)
Full text under the publisher's open licence · 230 words
Related coverage
FCC Chairman Brendan Carr’s war on the First Amendment
The Verge · Jul 23, 2026
On the Tradeoffs of On-Device Generative Models in Federated Predictive Maintenance Systems
arXiv · Oct 29, 2026
QFedPolyp: A Communication- and Inference-Efficient Federated Learning Framework for Polyp Segmentation
arXiv · Jul 28, 2026
FedGenSC: Federated Generative Semantic Communication with Channel-Aware Adaptation
arXiv · Sep 9, 2026