cs.ITNov 16, 2026

Practical Semantic Communication for General-Purpose Networks: Compression of High-Dimensional Embeddings Under Quantization

Authors: Leonardo Roque, Louis-Adrien Dufrène, Quentin Lampin, Grégoire Lefebvre, Mohamad Assaad

Organizations: Orange Research, France · Laboratoire des Signaux et Systèmes, CentraleSupélec, France

Abstract

This paper introduces a practical framework for semantic communication over wireless channels, focusing on the compression of high-dimensional embeddings under quantization and channel errors. Building upon a relaxed Gaussian Information Bottleneck (GIB) model, the approach provides analytical solutions for task-relevant information preservation, even with non-Gaussian targets. The framework relaxes traditional Gaussian assumptions, enabling effective compression for discrete and complex data such as text embeddings. It derives closed-form gradients for optimizing the compression matrix and establishes bounds linking continuous representations to discrete, noisy system performance. Comprehensive experiments on text classification tasks demonstrate that the proposed method outperforms task-agnostic quantization-based compression methods, maintaining high semantic fidelity at low bit budgets per embedding. The approach offers a scalable, interpretable, and resource-efficient solution for deploying semantic communication in general-purpose networks.

Figures & tables

Explore similar work

CardsList
  1. Benchmarking Wireless Representations: High-Dimensional vs. Compressed Embeddings for Efficiency and Robustness

    May 3, 2026Murilo Batista, Shirin Salehi, Saeed Mashdour +3Representation LearningEmbedding Compression

  2. Lossy Compressive Text Autoencoders

    Oct 7, 2026Vinko Sabolčec, Angelos Katharopoulos, David GrangierAutoencodersRepresentation Learning