Loading
Life sciences · Preprint
arXiv · September 8, 2026
Early or partial results. Treat as a signal, not a conclusion.
FedGenSC is a novel federated learning architecture for semantic communication that addresses three known failure modes in federated GAN training via a global generator, local discriminators, semantic prototype bank, and SNR-conditioned generation. Simulation experiments on a single language dataset and synthetic fading channel show relative BLEU-1 improvement over a baseline, but the work remains unpublished, unvalidated on real networks, and of algorithmic rather than clinical relevance.
Simulation study with ablation analysis. Intervention: FedGenSC: global generator with local discriminators, semantic prototype bank, SNR-conditioned generation. Compared with: FedDeepSC baseline.
FedGenSC achieved up to 58.2% relative improvement in BLEU-1 at 18 dB SNR over FedDeepSC baseline Method tested on Europarl dataset with K=10 clients under non-IID conditions (Dirichlet α=0.5) Ablation studies confirm independent contribution of each of three proposed components
Safety was not reported in the material analysed. Check the source before drawing any conclusion about harm.
The source did not state who this applies to in practice.
Early-stage algorithmic development with simulation-only evaluation on a single dataset and synthetic channel conditions; no real-world deployment, clinical outcome, or peer review.
As stated by the source record.
Quoted from the source exactly as published.
Graded across the dimensions that decide whether you should act, each from what the source actually supports. There is no single score, and where a dimension was not assessed it says so.
Integrating generative adversarial networks (GANs) into federated semantic communication (SemCom) is a natural progression, as generative priors can recover semantic fidelity under channel distortion that discriminative decoders cannot. However, naive GAN federation introduces three failure modes that prior work has, to the best of our knowledge, neither identified nor resolved: discriminator aggregation instability under non-independent and identically distributed (non-IID) data, semantic drift caused by divergent local embedding spaces, and channel-agnostic generation that cannot adapt to heterogeneous link conditions. We propose federated generative semantic communication (FedGenSC), which mitigates all three by employing a global generator with local-only discriminators, providing cross-client semantic information through a semantic prototype bank, and conditioning generation on the instantaneous signal-to-noise ratio (SNR). Experiments on the Europarl dataset over Rayleigh fading channels (K=10 clients, Dirichlet α=0.5) show that FedGenSC under non-IID data outperforms the FedDeepSC baseline across the tested SNR range, achieving up to a 58.2% relative improvement in bilingual evaluation understudy (BLEU)-1 at 18 dB. Ablation studies confirm the independent contribution of each component.
Taken from the source record, never inferred. Follow any of these and new work involving them reaches your briefing.