An Explainable Deep Semantic Coding for Binary-Classification- Oriented Communication

Semantic communication is emerging as a promising communication paradigm, where semantic coding plays an essential role by explicitly extracting task-critical information. Prior efforts toward semantic coding often rely on learning-based feature extraction methods but tend to overlook data compressi...

Full description

Saved in:
Bibliographic Details
Main Authors: Shuhui Wang, Zuxing Li, Xin Huang, Qi Jiang
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/9/4608
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850030826103767040
author Shuhui Wang
Zuxing Li
Xin Huang
Qi Jiang
author_facet Shuhui Wang
Zuxing Li
Xin Huang
Qi Jiang
author_sort Shuhui Wang
collection DOAJ
description Semantic communication is emerging as a promising communication paradigm, where semantic coding plays an essential role by explicitly extracting task-critical information. Prior efforts toward semantic coding often rely on learning-based feature extraction methods but tend to overlook data compression and lack a rigorous theoretical foundation. To address these limitations, this paper proposes a novel explainable deep semantic coding framework, considering a binary mixed source and a classification task at the receiver. From an information-theoretic perspective, we formulate a semantic coding problem that jointly optimizes data compression rate and classification accuracy subject to distortion constraints. To solve this problem, we leverage deep learning techniques and variational approximation methods to develop practical deep semantic coding schemes. Experiments on the CelebA dataset and the CIFAR-10 dataset demonstrate that the proposed schemes effectively balance data compression and binary classification accuracy, which aligns with the theoretical formulation.
format Article
id doaj-art-aeb240bfd10d4f5c9f98fdf371d1ae0a
institution DOAJ
issn 2076-3417
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-aeb240bfd10d4f5c9f98fdf371d1ae0a2025-08-20T02:59:07ZengMDPI AGApplied Sciences2076-34172025-04-01159460810.3390/app15094608An Explainable Deep Semantic Coding for Binary-Classification- Oriented CommunicationShuhui Wang0Zuxing Li1Xin Huang2Qi Jiang3College of Electronic and Information Engineering, Tongji University, Shanghai 201804, ChinaCollege of Electronic and Information Engineering, Tongji University, Shanghai 201804, ChinaCollege of Electronic and Information Engineering, Tongji University, Shanghai 201804, ChinaCollege of Electronic and Information Engineering, Tongji University, Shanghai 201804, ChinaSemantic communication is emerging as a promising communication paradigm, where semantic coding plays an essential role by explicitly extracting task-critical information. Prior efforts toward semantic coding often rely on learning-based feature extraction methods but tend to overlook data compression and lack a rigorous theoretical foundation. To address these limitations, this paper proposes a novel explainable deep semantic coding framework, considering a binary mixed source and a classification task at the receiver. From an information-theoretic perspective, we formulate a semantic coding problem that jointly optimizes data compression rate and classification accuracy subject to distortion constraints. To solve this problem, we leverage deep learning techniques and variational approximation methods to develop practical deep semantic coding schemes. Experiments on the CelebA dataset and the CIFAR-10 dataset demonstrate that the proposed schemes effectively balance data compression and binary classification accuracy, which aligns with the theoretical formulation.https://www.mdpi.com/2076-3417/15/9/4608semantic communicationsemantic codingdeep learningvariational methodimage classification
spellingShingle Shuhui Wang
Zuxing Li
Xin Huang
Qi Jiang
An Explainable Deep Semantic Coding for Binary-Classification- Oriented Communication
Applied Sciences
semantic communication
semantic coding
deep learning
variational method
image classification
title An Explainable Deep Semantic Coding for Binary-Classification- Oriented Communication
title_full An Explainable Deep Semantic Coding for Binary-Classification- Oriented Communication
title_fullStr An Explainable Deep Semantic Coding for Binary-Classification- Oriented Communication
title_full_unstemmed An Explainable Deep Semantic Coding for Binary-Classification- Oriented Communication
title_short An Explainable Deep Semantic Coding for Binary-Classification- Oriented Communication
title_sort explainable deep semantic coding for binary classification oriented communication
topic semantic communication
semantic coding
deep learning
variational method
image classification
url https://www.mdpi.com/2076-3417/15/9/4608
work_keys_str_mv AT shuhuiwang anexplainabledeepsemanticcodingforbinaryclassificationorientedcommunication
AT zuxingli anexplainabledeepsemanticcodingforbinaryclassificationorientedcommunication
AT xinhuang anexplainabledeepsemanticcodingforbinaryclassificationorientedcommunication
AT qijiang anexplainabledeepsemanticcodingforbinaryclassificationorientedcommunication
AT shuhuiwang explainabledeepsemanticcodingforbinaryclassificationorientedcommunication
AT zuxingli explainabledeepsemanticcodingforbinaryclassificationorientedcommunication
AT xinhuang explainabledeepsemanticcodingforbinaryclassificationorientedcommunication
AT qijiang explainabledeepsemanticcodingforbinaryclassificationorientedcommunication