A Survey on Robust Deep Joint Source-Channel Coding for Semantic Communications

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hong, Eunhye, Park, Taewoo, Kim, Yongjune
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908939652694016
author Hong, Eunhye
Park, Taewoo
Kim, Yongjune
author_facet Hong, Eunhye
Park, Taewoo
Kim, Yongjune
contents Semantic communications (SCs) aim to transmit only the essential information required to perform given tasks, thereby improving communication efficiency. Deep learning-based joint source-channel coding (deep JSCC) has emerged as a promising approach for SC systems; however, its performance often degrades when the deployment channels differ from the training channel conditions, making robustness a critical requirement. This paper presents a structured overview of recent methodologies for enhancing the robustness of deep JSCC. Specifically, existing approaches are categorized into two classes: robust training approaches and adaptive approaches, with the latter further divided into adaptive semantic feature selection, physical-layer adaptation, and semantic feature adaptation. Finally, we discuss promising directions, including multi-task generalization and explainability in robust SC systems.
format Preprint
id arxiv_https___arxiv_org_abs_2604_04413
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A Survey on Robust Deep Joint Source-Channel Coding for Semantic Communications
Hong, Eunhye
Park, Taewoo
Kim, Yongjune
Signal Processing
Semantic communications (SCs) aim to transmit only the essential information required to perform given tasks, thereby improving communication efficiency. Deep learning-based joint source-channel coding (deep JSCC) has emerged as a promising approach for SC systems; however, its performance often degrades when the deployment channels differ from the training channel conditions, making robustness a critical requirement. This paper presents a structured overview of recent methodologies for enhancing the robustness of deep JSCC. Specifically, existing approaches are categorized into two classes: robust training approaches and adaptive approaches, with the latter further divided into adaptive semantic feature selection, physical-layer adaptation, and semantic feature adaptation. Finally, we discuss promising directions, including multi-task generalization and explainability in robust SC systems.
title A Survey on Robust Deep Joint Source-Channel Coding for Semantic Communications
topic Signal Processing
url https://arxiv.org/abs/2604.04413