Low-Latency Generative Semantic Communication via Channel-Realization Flow Matching

2026-07-27

AI Summary

Existing generative semantic communication receivers suffer from high decoding latency and insufficient robustness due to reliance on stochastic iterative decoding or independent coupling mechanisms that ignore channel correlations. This work proposes a Realizable Coupled Bridge Flow Matching (RC-BFM) approach, formulating semantic recovery at the receiver as a coupled flow matching problem under bandwidth and power constraints. By introducing channel-aware semantic state initialization and constructing training pairs via realizable coupled entropy-optimal transport, RC-BFM ensures consistency across channel realizations. Theoretical analysis identifies independent coupling as the root cause of train-test distribution shift and proves that the end-to-end distortion bound decays as O(K⁻²) with the number of discrete steps K. Experiments on CIFAR-10 and FFHQ-64 under AWGN and Rayleigh fading channels demonstrate that RC-BFM achieves over 10× lower decoding latency than diffusion models while preserving high fidelity and perceptual quality.

Abstract

Generative semantic communication receivers deliver high perceptual quality but suffer from prohibitive decoding latency. This bottleneck arises because diffusion receivers rely on stochastic iterative decoding, while existing flow matching receivers employ independent endpoint coupling that ignores the physical source--channel link, yielding unnecessarily long and curved sampling trajectories. In this paper, we reformulate receiver-side recovery as a realization-coupled bridge flow matching problem under explicit bandwidth and power constraints. Specifically, we propose Realization-Coupled Bridge Flow Matching (RC-BFM), where the decoder initializes from a channel-induced semantic state rather than isotropic noise. Crucially, training pairs are linked via a realization-coupled entropic optimal transport (RC-OT) plan that preserves the physical channel realization of each transmission while maintaining robustness to stochastic fading. Furthermore, we identify independent coupling as the fundamental source of a conditional train--test distribution shift in conditional flow matching-based receivers, and derive an end-to-end distortion bound whose discretization error decays as \(O(K^{-2})\). Experiments on CIFAR-10 and FFHQ-64\(\times\)64 over AWGN and Rayleigh fading channels demonstrate that RC-BFM achieves a superior fidelity--perception trade-off, reducing decoding latency by over 10\(\times\) compared to diffusion-based receivers.

Problem

• semantic communication
• decoding latency
• flow matching
• channel realization
• generative models

Innovation

• Realization-Coupled Flow Matching
• Semantic Communication
• Low-Latency Decoding
• Entropic Optimal Transport
• Channel-Aware Generation