A Deep Variational Approach to Multiterminal Joint Source-Channel Coding Based on Information Bottleneck Principle

In this article, we concentrate on a generic multiterminal joint source-channel coding scenario, appearing in a wide variety of real-world applications. Specifically, several noisy observations from a source signal must be compressed at some intermediate nodes, before getting forwarded over multiple...

Full description

Saved in:
Bibliographic Details
Main Authors: Shayan Hassanpour, Matthias Hummert, Dirk Wubben, Armin Dekorsy
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Open Journal of the Communications Society
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11005413/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849761632938360832
author Shayan Hassanpour
Matthias Hummert
Dirk Wubben
Armin Dekorsy
author_facet Shayan Hassanpour
Matthias Hummert
Dirk Wubben
Armin Dekorsy
author_sort Shayan Hassanpour
collection DOAJ
description In this article, we concentrate on a generic multiterminal joint source-channel coding scenario, appearing in a wide variety of real-world applications. Specifically, several noisy observations from a source signal must be compressed at some intermediate nodes, before getting forwarded over multiple error-prone and rate-limited channels towards a (remote) processing unit. The imperfections of the forward channels should be integrated into the design of (local) compressor units. By following the Information Bottleneck principle, the Mutual Information is selected here as the fidelity criterion, and a novel (data-driven) design approach is presented for two distinct types of processing flow/strategy at the remote unit. To that end, tractable objective functions are developed, together with the pertinent learning architectures, generalizing the concepts of Variational Auto-Encoders and (Distributed) Deep Variational Information Bottleneck for (remote) source coding to the context of distributed joint source-channel coding. Unlike the conventional approaches, the proposed schemes here work based upon a finite sample set, thereby obviating the call for full prior knowledge of the joint statistics of input signals. The effectiveness of these novel sample-based compression schemes is substantiated as well by a couple of simulations over typical transmission setups.
format Article
id doaj-art-c32e49cb262e4f2c87bf9119b8db9ef5
institution DOAJ
issn 2644-125X
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Open Journal of the Communications Society
spelling doaj-art-c32e49cb262e4f2c87bf9119b8db9ef52025-08-20T03:05:57ZengIEEEIEEE Open Journal of the Communications Society2644-125X2025-01-0164462447510.1109/OJCOMS.2025.357044611005413A Deep Variational Approach to Multiterminal Joint Source-Channel Coding Based on Information Bottleneck PrincipleShayan Hassanpour0https://orcid.org/0000-0003-2598-0415Matthias Hummert1https://orcid.org/0000-0003-2561-161XDirk Wubben2https://orcid.org/0000-0003-3854-6140Armin Dekorsy3https://orcid.org/0000-0002-5790-1470Department of Communications Engineering, University of Bremen, Bremen, GermanyDepartment of Communications Engineering, University of Bremen, Bremen, GermanyDepartment of Communications Engineering, University of Bremen, Bremen, GermanyDepartment of Communications Engineering, University of Bremen, Bremen, GermanyIn this article, we concentrate on a generic multiterminal joint source-channel coding scenario, appearing in a wide variety of real-world applications. Specifically, several noisy observations from a source signal must be compressed at some intermediate nodes, before getting forwarded over multiple error-prone and rate-limited channels towards a (remote) processing unit. The imperfections of the forward channels should be integrated into the design of (local) compressor units. By following the Information Bottleneck principle, the Mutual Information is selected here as the fidelity criterion, and a novel (data-driven) design approach is presented for two distinct types of processing flow/strategy at the remote unit. To that end, tractable objective functions are developed, together with the pertinent learning architectures, generalizing the concepts of Variational Auto-Encoders and (Distributed) Deep Variational Information Bottleneck for (remote) source coding to the context of distributed joint source-channel coding. Unlike the conventional approaches, the proposed schemes here work based upon a finite sample set, thereby obviating the call for full prior knowledge of the joint statistics of input signals. The effectiveness of these novel sample-based compression schemes is substantiated as well by a couple of simulations over typical transmission setups.https://ieeexplore.ieee.org/document/11005413/6Gauto-encodersdeep learninginformation bottleneckjoint source-channel coding
spellingShingle Shayan Hassanpour
Matthias Hummert
Dirk Wubben
Armin Dekorsy
A Deep Variational Approach to Multiterminal Joint Source-Channel Coding Based on Information Bottleneck Principle
IEEE Open Journal of the Communications Society
6G
auto-encoders
deep learning
information bottleneck
joint source-channel coding
title A Deep Variational Approach to Multiterminal Joint Source-Channel Coding Based on Information Bottleneck Principle
title_full A Deep Variational Approach to Multiterminal Joint Source-Channel Coding Based on Information Bottleneck Principle
title_fullStr A Deep Variational Approach to Multiterminal Joint Source-Channel Coding Based on Information Bottleneck Principle
title_full_unstemmed A Deep Variational Approach to Multiterminal Joint Source-Channel Coding Based on Information Bottleneck Principle
title_short A Deep Variational Approach to Multiterminal Joint Source-Channel Coding Based on Information Bottleneck Principle
title_sort deep variational approach to multiterminal joint source channel coding based on information bottleneck principle
topic 6G
auto-encoders
deep learning
information bottleneck
joint source-channel coding
url https://ieeexplore.ieee.org/document/11005413/
work_keys_str_mv AT shayanhassanpour adeepvariationalapproachtomultiterminaljointsourcechannelcodingbasedoninformationbottleneckprinciple
AT matthiashummert adeepvariationalapproachtomultiterminaljointsourcechannelcodingbasedoninformationbottleneckprinciple
AT dirkwubben adeepvariationalapproachtomultiterminaljointsourcechannelcodingbasedoninformationbottleneckprinciple
AT armindekorsy adeepvariationalapproachtomultiterminaljointsourcechannelcodingbasedoninformationbottleneckprinciple
AT shayanhassanpour deepvariationalapproachtomultiterminaljointsourcechannelcodingbasedoninformationbottleneckprinciple
AT matthiashummert deepvariationalapproachtomultiterminaljointsourcechannelcodingbasedoninformationbottleneckprinciple
AT dirkwubben deepvariationalapproachtomultiterminaljointsourcechannelcodingbasedoninformationbottleneckprinciple
AT armindekorsy deepvariationalapproachtomultiterminaljointsourcechannelcodingbasedoninformationbottleneckprinciple