Channel-Aware Vector Quantization for Robust Semantic Communication on Discrete Channels Article Swipe

PDF

Zian Meng , Qiang Li , W.H. Wilson Tang , Mengyi Yan , Xiaohu Ge ·

YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2510.18604

Deep learning-based semantic communication has largely relied on analog or semi-digital transmission, which limits compatibility with modern digital communication infrastructures. Recent studies have employed vector quantization (VQ) to enable discrete semantic transmission, yet existing methods neglect channel state information during codebook optimization, leading to suboptimal robustness. To bridge this gap, we propose a channel-aware vector quantization (CAVQ) algorithm within a joint source-channel coding (JSCC) framework, termed VQJSCC, established on a discrete memoryless channel. In this framework, semantic features are discretized and directly mapped to modulation constellation symbols, while CAVQ integrates channel transition probabilities into the quantization process, aligning easily confused symbols with semantically similar codewords. A multi-codebook alignment mechanism is further introduced to handle mismatches between codebook order and modulation order by decomposing the transmission stream into multiple independently optimized subchannels. Experimental results demonstrate that VQJSCC effectively mitigates the digital cliff effect, achieves superior reconstruction quality across various modulation schemes, and outperforms state-of-the-art digital semantic communication baselines in both robustness and efficiency.

Related Topics

Disease Vector

Color Quantization

Support Vector Machine

Kriss Vector

Vector Graphics

Vector (Mathematics And Physics)

Poynting Vector

Vector Projection

Quantization (Signal Processing)

Vector Calculus

Landau Quantization

Vector W8

Concepts

No concepts available.

Metadata

Type: preprint
Landing Page: http://arxiv.org/abs/2510.18604
PDF: https://arxiv.org/pdf/2510.18604
OA Status: green
OpenAlex ID: https://openalex.org/W4416056744

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4416056744

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2510.18604

Digital Object Identifier
Title: Channel-Aware Vector Quantization for Robust Semantic Communication on Discrete Channels

Work title
Type: preprint

OpenAlex work type
Publication year: 2025

Year of publication
Publication date: 2025-10-21

Full publication date if available
Authors: Zian Meng, Qiang Li, W.H. Wilson Tang, Mengyi Yan, Xiaohu Ge

List of authors in order
Landing page: https://arxiv.org/abs/2510.18604

Publisher landing page
PDF URL: https://arxiv.org/pdf/2510.18604

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: green

Open access status per OpenAlex
OA URL: https://arxiv.org/pdf/2510.18604

Direct OA link when available
Cited by: 0

Total citation count in OpenAlex

Full payload

id	https://openalex.org/W4416056744
doi	https://doi.org/10.48550/arxiv.2510.18604
ids.doi	https://doi.org/10.48550/arxiv.2510.18604
ids.openalex	https://openalex.org/W4416056744
fwci
type	preprint
title	Channel-Aware Vector Quantization for Robust Semantic Communication on Discrete Channels
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
is_xpac	False
apc_list
apc_paid
language
locations[0].id	pmh:oai:arXiv.org:2510.18604
locations[0].is_oa	True
locations[0].source.id	https://openalex.org/S4306400194
locations[0].source.issn
locations[0].source.type	repository
locations[0].source.is_oa	True
locations[0].source.issn_l
locations[0].source.is_core	False
locations[0].source.is_in_doaj	False
locations[0].source.display_name	arXiv (Cornell University)
locations[0].source.host_organization	https://openalex.org/I205783295
locations[0].source.host_organization_name	Cornell University
locations[0].source.host_organization_lineage	https://openalex.org/I205783295
locations[0].license
locations[0].pdf_url	https://arxiv.org/pdf/2510.18604
locations[0].version	submittedVersion
locations[0].raw_type	text
locations[0].license_id
locations[0].is_accepted	False
locations[0].is_published	False
locations[0].raw_source_name
locations[0].landing_page_url	http://arxiv.org/abs/2510.18604
locations[1].id	doi:10.48550/arxiv.2510.18604
locations[1].is_oa	True
locations[1].source.id	https://openalex.org/S4306400194
locations[1].source.issn
locations[1].source.type	repository
locations[1].source.is_oa	True
locations[1].source.issn_l
locations[1].source.is_core	False
locations[1].source.is_in_doaj	False
locations[1].source.display_name	arXiv (Cornell University)
locations[1].source.host_organization	https://openalex.org/I205783295
locations[1].source.host_organization_name	Cornell University
locations[1].source.host_organization_lineage	https://openalex.org/I205783295
locations[1].license
locations[1].pdf_url
locations[1].version
locations[1].raw_type	article
locations[1].license_id
locations[1].is_accepted	False
locations[1].is_published
locations[1].raw_source_name
locations[1].landing_page_url	https://doi.org/10.48550/arxiv.2510.18604
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5102629811
authorships[0].author.orcid
authorships[0].author.display_name	Zian Meng
authorships[0].author_position	first
authorships[0].raw_author_name	Meng, Zian
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5114221508
authorships[1].author.orcid
authorships[1].author.display_name	Qiang Li
authorships[1].author_position	middle
authorships[1].raw_author_name	Li, Qiang
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5035023430
authorships[2].author.orcid	https://orcid.org/0000-0002-8335-735X
authorships[2].author.display_name	W.H. Wilson Tang
authorships[2].author_position	middle
authorships[2].raw_author_name	Tang, Wenqian
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5002103818
authorships[3].author.orcid
authorships[3].author.display_name	Mengyi Yan
authorships[3].author_position	middle
authorships[3].raw_author_name	Yan, Mingdie
authorships[3].is_corresponding	False
authorships[4].author.id	https://openalex.org/A5057308968
authorships[4].author.orcid	https://orcid.org/0000-0002-3204-5241
authorships[4].author.display_name	Xiaohu Ge
authorships[4].author_position	last
authorships[4].raw_author_name	Ge, Xiaohu
authorships[4].is_corresponding	False
has_content.pdf	False
has_content.grobid_xml	False
is_paratext	False
open_access.is_oa	True
open_access.oa_url	https://arxiv.org/pdf/2510.18604
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-10-24T00:00:00
display_name	Channel-Aware Vector Quantization for Robust Semantic Communication on Discrete Channels
has_fulltext	False
is_retracted	False
updated_date	2025-11-28T10:37:17.876367
primary_topic
cited_by_count	0
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2510.18604
best_oa_location.is_oa	True
best_oa_location.source.id	https://openalex.org/S4306400194
best_oa_location.source.issn
best_oa_location.source.type	repository
best_oa_location.source.is_oa	True
best_oa_location.source.issn_l
best_oa_location.source.is_core	False
best_oa_location.source.is_in_doaj	False
best_oa_location.source.display_name	arXiv (Cornell University)
best_oa_location.source.host_organization	https://openalex.org/I205783295
best_oa_location.source.host_organization_name	Cornell University
best_oa_location.source.host_organization_lineage	https://openalex.org/I205783295
best_oa_location.license
best_oa_location.pdf_url	https://arxiv.org/pdf/2510.18604
best_oa_location.version	submittedVersion
best_oa_location.raw_type	text
best_oa_location.license_id
best_oa_location.is_accepted	False
best_oa_location.is_published	False
best_oa_location.raw_source_name
best_oa_location.landing_page_url	http://arxiv.org/abs/2510.18604
primary_location.id	pmh:oai:arXiv.org:2510.18604
primary_location.is_oa	True
primary_location.source.id	https://openalex.org/S4306400194
primary_location.source.issn
primary_location.source.type	repository
primary_location.source.is_oa	True
primary_location.source.issn_l
primary_location.source.is_core	False
primary_location.source.is_in_doaj	False
primary_location.source.display_name	arXiv (Cornell University)
primary_location.source.host_organization	https://openalex.org/I205783295
primary_location.source.host_organization_name	Cornell University
primary_location.source.host_organization_lineage	https://openalex.org/I205783295
primary_location.license
primary_location.pdf_url	https://arxiv.org/pdf/2510.18604
primary_location.version	submittedVersion
primary_location.raw_type	text
primary_location.license_id
primary_location.is_accepted	False
primary_location.is_published	False
primary_location.raw_source_name
primary_location.landing_page_url	http://arxiv.org/abs/2510.18604
publication_date	2025-10-21
publication_year	2025
referenced_works_count	0
abstract_inverted_index.A	105
abstract_inverted_index.a	52, 59, 69
abstract_inverted_index.In	73
abstract_inverted_index.To	46
abstract_inverted_index.by	121
abstract_inverted_index.in	157
abstract_inverted_index.is	109
abstract_inverted_index.on	7, 68
abstract_inverted_index.or	9
abstract_inverted_index.to	27, 43, 83, 112
abstract_inverted_index.we	50
abstract_inverted_index.and	80, 118, 150, 160
abstract_inverted_index.are	78
abstract_inverted_index.has	4
abstract_inverted_index.the	94, 123, 138
abstract_inverted_index.yet	32
abstract_inverted_index.(VQ)	26
abstract_inverted_index.CAVQ	88
abstract_inverted_index.Deep	0
abstract_inverted_index.both	158
abstract_inverted_index.gap,	49
abstract_inverted_index.have	22
abstract_inverted_index.into	93, 126
abstract_inverted_index.that	134
abstract_inverted_index.this	48, 74
abstract_inverted_index.with	15, 101
abstract_inverted_index.cliff	140
abstract_inverted_index.joint	60
abstract_inverted_index.order	117, 120
abstract_inverted_index.state	37
abstract_inverted_index.which	12
abstract_inverted_index.while	87
abstract_inverted_index.(CAVQ)	56
abstract_inverted_index.(JSCC)	63
abstract_inverted_index.Recent	20
abstract_inverted_index.VQJSCC	135
abstract_inverted_index.across	146
abstract_inverted_index.analog	8
abstract_inverted_index.bridge	47
abstract_inverted_index.coding	62
abstract_inverted_index.during	39
abstract_inverted_index.easily	98
abstract_inverted_index.enable	28
abstract_inverted_index.handle	113
abstract_inverted_index.limits	13
abstract_inverted_index.mapped	82
abstract_inverted_index.modern	16
abstract_inverted_index.relied	6
abstract_inverted_index.stream	125
abstract_inverted_index.termed	65
abstract_inverted_index.vector	24, 54
abstract_inverted_index.within	58
abstract_inverted_index.VQJSCC,	66
abstract_inverted_index.between	115
abstract_inverted_index.channel	36, 90
abstract_inverted_index.digital	17, 139, 153
abstract_inverted_index.effect,	141
abstract_inverted_index.further	110
abstract_inverted_index.largely	5
abstract_inverted_index.leading	42
abstract_inverted_index.methods	34
abstract_inverted_index.neglect	35
abstract_inverted_index.propose	51
abstract_inverted_index.quality	145
abstract_inverted_index.results	132
abstract_inverted_index.similar	103
abstract_inverted_index.studies	21
abstract_inverted_index.symbols	100
abstract_inverted_index.various	147
abstract_inverted_index.achieves	142
abstract_inverted_index.aligning	97
abstract_inverted_index.channel.	72
abstract_inverted_index.codebook	40, 116
abstract_inverted_index.confused	99
abstract_inverted_index.directly	81
abstract_inverted_index.discrete	29, 70
abstract_inverted_index.employed	23
abstract_inverted_index.existing	33
abstract_inverted_index.features	77
abstract_inverted_index.multiple	127
abstract_inverted_index.process,	96
abstract_inverted_index.schemes,	149
abstract_inverted_index.semantic	2, 30, 76, 154
abstract_inverted_index.superior	143
abstract_inverted_index.symbols,	86
abstract_inverted_index.algorithm	57
abstract_inverted_index.alignment	107
abstract_inverted_index.baselines	156
abstract_inverted_index.mechanism	108
abstract_inverted_index.mitigates	137
abstract_inverted_index.optimized	129
abstract_inverted_index.codewords.	104
abstract_inverted_index.framework,	64, 75
abstract_inverted_index.integrates	89
abstract_inverted_index.introduced	111
abstract_inverted_index.memoryless	71
abstract_inverted_index.mismatches	114
abstract_inverted_index.modulation	84, 119, 148
abstract_inverted_index.robustness	159
abstract_inverted_index.suboptimal	44
abstract_inverted_index.transition	91
abstract_inverted_index.decomposing	122
abstract_inverted_index.demonstrate	133
abstract_inverted_index.discretized	79
abstract_inverted_index.effectively	136
abstract_inverted_index.efficiency.	161
abstract_inverted_index.established	67
abstract_inverted_index.information	38
abstract_inverted_index.outperforms	151
abstract_inverted_index.robustness.	45
abstract_inverted_index.Experimental	131
abstract_inverted_index.quantization	25, 55, 95
abstract_inverted_index.semantically	102
abstract_inverted_index.semi-digital	10
abstract_inverted_index.subchannels.	130
abstract_inverted_index.transmission	124
abstract_inverted_index.channel-aware	53
abstract_inverted_index.communication	3, 18, 155
abstract_inverted_index.compatibility	14
abstract_inverted_index.constellation	85
abstract_inverted_index.independently	128
abstract_inverted_index.optimization,	41
abstract_inverted_index.probabilities	92
abstract_inverted_index.transmission,	11, 31
abstract_inverted_index.learning-based	1
abstract_inverted_index.multi-codebook	106
abstract_inverted_index.reconstruction	144
abstract_inverted_index.source-channel	61
abstract_inverted_index.infrastructures.	19
abstract_inverted_index.state-of-the-art	152
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	5
citation_normalized_percentile