English

Topology-Preserving Deep Joint Source-Channel Coding for Semantic Communication

Machine Learning 2026-03-19 v1 Information Theory Image and Video Processing math.IT

Abstract

Many wireless vision applications, such as autonomous driving, require preservation of global structural information rather than only per-pixel fidelity. However, existing Deep joint source-channel coding (DeepJSCC) schemes mainly optimize pixel-wise losses and provide no explicit protection of connectivity or topology. This letter proposes TopoJSCC, a topology-aware DeepJSCC framework that integrates persistent-homology regularizers to end-to-end training. Specifically, we enforce topological consistency by penalizing Wasserstein distances between cubical persistence diagrams of original and reconstructed images, and between Vietoris--Rips persistence of latent features before and after the channel to promote a robust latent manifold. TopoJSCC is based on end-to-end learning and requires no side information. Experiments show improved topology preservation and peak signal-to-noise ratio (PSNR) in low signal-to-noise ratio (SNR) and bandwidth-ratio regimes.

Keywords

Cite

@article{arxiv.2603.17126,
  title  = {Topology-Preserving Deep Joint Source-Channel Coding for Semantic Communication},
  author = {Omar Erak and Omar Alhussein and Fang Fang and Sami Muhaidat},
  journal= {arXiv preprint arXiv:2603.17126},
  year   = {2026}
}

Comments

Submitted to IEEE Journals for possible publication

R2 v1 2026-07-01T11:25:09.948Z