Class-aware contrastive optimization for imbalanced text classification Article Swipe

PDF

Grigorii Khvatskii , Nuno Moniz , Khoa D. Doan , Nitesh V. Chawla ·

YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.1007/s44248-025-00064-0

The unique characteristics of text data make classification tasks a complex problem. Advances in unsupervised and semi-supervised learning and autoencoder architectures addressed several challenges. However, they still struggle with imbalanced text classification tasks, a common scenario in real-world applications, demonstrating a tendency to produce embeddings with unfavorable properties, such as class overlap. In this paper, we show that leveraging class-aware contrastive optimization combined with denoising autoencoders can successfully tackle imbalanced text classification tasks, achieving better performance than the other strong text classification models. Concretely, our proposal combines reconstruction loss with contrastive class separation in the embedding space, allowing a better balance between the truthfulness of the generated embeddings and the model’s ability to separate different classes. Compared with an extensive set of traditional and deep learning based competing methods, our proposal demonstrates a notable increase in performance across a wide variety of text datasets.

Related Topics

Computer Science

Artificial Intelligence

Concepts

Computer science Artificial intelligence Class (philosophy) Natural language processing

Metadata

Type: article
Language: en
Landing Page: https://doi.org/10.1007/s44248-025-00064-0
PDF: https://link.springer.com/content/pdf/10.1007/s44248-025-00064-0.pdf
OA Status: diamond
References: 45
Related Works: 10
OpenAlex ID: https://openalex.org/W4411878237

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4411878237

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.1007/s44248-025-00064-0

Digital Object Identifier
Title: Class-aware contrastive optimization for imbalanced text classification

Work title
Type: article

OpenAlex work type
Language: en

Primary language
Publication year: 2025

Year of publication
Publication date: 2025-07-01

Full publication date if available
Authors: Grigorii Khvatskii, Nuno Moniz, Khoa D. Doan, Nitesh V. Chawla

List of authors in order
Landing page: https://doi.org/10.1007/s44248-025-00064-0

Publisher landing page
PDF URL: https://link.springer.com/content/pdf/10.1007/s44248-025-00064-0.pdf

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: diamond

Open access status per OpenAlex
OA URL: https://link.springer.com/content/pdf/10.1007/s44248-025-00064-0.pdf

Direct OA link when available
Concepts: Computer science, Artificial intelligence, Class (philosophy), Natural language processing

Top concepts (fields/topics) attached by OpenAlex
Cited by: 0

Total citation count in OpenAlex
References (count): 45

Number of works referenced by this work
Related works (count): 10

Other works algorithmically related by OpenAlex

Full payload

id	https://openalex.org/W4411878237
doi	https://doi.org/10.1007/s44248-025-00064-0
ids.doi	https://doi.org/10.1007/s44248-025-00064-0
ids.openalex	https://openalex.org/W4411878237
fwci	0.0
type	article
title	Class-aware contrastive optimization for imbalanced text classification
biblio.issue	1
biblio.volume	3
biblio.last_page
biblio.first_page
topics[0].id	https://openalex.org/T11652
topics[0].field.id	https://openalex.org/fields/17
topics[0].field.display_name	Computer Science
topics[0].score	0.9990000128746033
topics[0].domain.id	https://openalex.org/domains/3
topics[0].domain.display_name	Physical Sciences
topics[0].subfield.id	https://openalex.org/subfields/1702
topics[0].subfield.display_name	Artificial Intelligence
topics[0].display_name	Imbalanced Data Classification Techniques
topics[1].id	https://openalex.org/T11550
topics[1].field.id	https://openalex.org/fields/17
topics[1].field.display_name	Computer Science
topics[1].score	0.9980000257492065
topics[1].domain.id	https://openalex.org/domains/3
topics[1].domain.display_name	Physical Sciences
topics[1].subfield.id	https://openalex.org/subfields/1702
topics[1].subfield.display_name	Artificial Intelligence
topics[1].display_name	Text and Document Classification Technologies
topics[2].id	https://openalex.org/T11644
topics[2].field.id	https://openalex.org/fields/17
topics[2].field.display_name	Computer Science
topics[2].score	0.9976999759674072
topics[2].domain.id	https://openalex.org/domains/3
topics[2].domain.display_name	Physical Sciences
topics[2].subfield.id	https://openalex.org/subfields/1710
topics[2].subfield.display_name	Information Systems
topics[2].display_name	Spam and Phishing Detection
is_xpac	False
apc_list
apc_paid
concepts[0].id	https://openalex.org/C41008148
concepts[0].level	0
concepts[0].score	0.58111971616745
concepts[0].wikidata	https://www.wikidata.org/wiki/Q21198
concepts[0].display_name	Computer science
concepts[1].id	https://openalex.org/C154945302
concepts[1].level	1
concepts[1].score	0.556442379951477
concepts[1].wikidata	https://www.wikidata.org/wiki/Q11660
concepts[1].display_name	Artificial intelligence
concepts[2].id	https://openalex.org/C2777212361
concepts[2].level	2
concepts[2].score	0.5266754031181335
concepts[2].wikidata	https://www.wikidata.org/wiki/Q5127848
concepts[2].display_name	Class (philosophy)
concepts[3].id	https://openalex.org/C204321447
concepts[3].level	1
concepts[3].score	0.45682811737060547
concepts[3].wikidata	https://www.wikidata.org/wiki/Q30642
concepts[3].display_name	Natural language processing
keywords[0].id	https://openalex.org/keywords/computer-science
keywords[0].score	0.58111971616745
keywords[0].display_name	Computer science
keywords[1].id	https://openalex.org/keywords/artificial-intelligence
keywords[1].score	0.556442379951477
keywords[1].display_name	Artificial intelligence
keywords[2].id	https://openalex.org/keywords/class
keywords[2].score	0.5266754031181335
keywords[2].display_name	Class (philosophy)
keywords[3].id	https://openalex.org/keywords/natural-language-processing
keywords[3].score	0.45682811737060547
keywords[3].display_name	Natural language processing
language	en
locations[0].id	doi:10.1007/s44248-025-00064-0
locations[0].is_oa	True
locations[0].source.id	https://openalex.org/S4387287783
locations[0].source.issn	2731-6955
locations[0].source.type	journal
locations[0].source.is_oa	True
locations[0].source.issn_l	2731-6955
locations[0].source.is_core	True
locations[0].source.is_in_doaj	True
locations[0].source.display_name	Discover Data
locations[0].source.host_organization	https://openalex.org/P4310319900
locations[0].source.host_organization_name	Springer Science+Business Media
locations[0].source.host_organization_lineage	https://openalex.org/P4310319900, https://openalex.org/P4310319965
locations[0].source.host_organization_lineage_names	Springer Science+Business Media, Springer Nature
locations[0].license	cc-by-nc-nd
locations[0].pdf_url	https://link.springer.com/content/pdf/10.1007/s44248-025-00064-0.pdf
locations[0].version	publishedVersion
locations[0].raw_type	journal-article
locations[0].license_id	https://openalex.org/licenses/cc-by-nc-nd
locations[0].is_accepted	True
locations[0].is_published	True
locations[0].raw_source_name	Discover Data
locations[0].landing_page_url	https://doi.org/10.1007/s44248-025-00064-0
locations[1].id	pmh:oai:doaj.org/article:7a11592f5f204d68ad281eab87257078
locations[1].is_oa	False
locations[1].source.id	https://openalex.org/S4306401280
locations[1].source.issn
locations[1].source.type	repository
locations[1].source.is_oa	False
locations[1].source.issn_l
locations[1].source.is_core	False
locations[1].source.is_in_doaj	False
locations[1].source.display_name	DOAJ (DOAJ: Directory of Open Access Journals)
locations[1].source.host_organization
locations[1].source.host_organization_name
locations[1].license
locations[1].pdf_url
locations[1].version	submittedVersion
locations[1].raw_type	article
locations[1].license_id
locations[1].is_accepted	False
locations[1].is_published	False
locations[1].raw_source_name	Discover Data, Vol 3, Iss 1, Pp 1-22 (2025)
locations[1].landing_page_url	https://doaj.org/article/7a11592f5f204d68ad281eab87257078
indexed_in	crossref, doaj
authorships[0].author.id	https://openalex.org/A5114633670
authorships[0].author.orcid
authorships[0].author.display_name	Grigorii Khvatskii
authorships[0].author_position	first
authorships[0].raw_author_name	Grigorii Khvatskii
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5047689411
authorships[1].author.orcid	https://orcid.org/0000-0003-4322-1076
authorships[1].author.display_name	Nuno Moniz
authorships[1].author_position	middle
authorships[1].raw_author_name	Nuno Moniz
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5080642445
authorships[2].author.orcid	https://orcid.org/0000-0002-1610-8206
authorships[2].author.display_name	Khoa D. Doan
authorships[2].author_position	middle
authorships[2].raw_author_name	Khoa D. Doan
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5068157871
authorships[3].author.orcid	https://orcid.org/0000-0003-3932-5956
authorships[3].author.display_name	Nitesh V. Chawla
authorships[3].author_position	last
authorships[3].raw_author_name	Nitesh V. Chawla
authorships[3].is_corresponding	False
has_content.pdf	True
has_content.grobid_xml	True
is_paratext	False
open_access.is_oa	True
open_access.oa_url	https://link.springer.com/content/pdf/10.1007/s44248-025-00064-0.pdf
open_access.oa_status	diamond
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	Class-aware contrastive optimization for imbalanced text classification
has_fulltext	False
is_retracted	False
updated_date	2025-11-06T03:46:38.306776
primary_topic.id	https://openalex.org/T11652
primary_topic.field.id	https://openalex.org/fields/17
primary_topic.field.display_name	Computer Science
primary_topic.score	0.9990000128746033
primary_topic.domain.id	https://openalex.org/domains/3
primary_topic.domain.display_name	Physical Sciences
primary_topic.subfield.id	https://openalex.org/subfields/1702
primary_topic.subfield.display_name	Artificial Intelligence
primary_topic.display_name	Imbalanced Data Classification Techniques
related_works	https://openalex.org/W4391375266, https://openalex.org/W2899084033, https://openalex.org/W2748952813, https://openalex.org/W2390279801, https://openalex.org/W4391913857, https://openalex.org/W2358668433, https://openalex.org/W4396701345, https://openalex.org/W2376932109, https://openalex.org/W2001405890, https://openalex.org/W3204019825
cited_by_count	0
locations_count	2
best_oa_location.id	doi:10.1007/s44248-025-00064-0
best_oa_location.is_oa	True
best_oa_location.source.id	https://openalex.org/S4387287783
best_oa_location.source.issn	2731-6955
best_oa_location.source.type	journal
best_oa_location.source.is_oa	True
best_oa_location.source.issn_l	2731-6955
best_oa_location.source.is_core	True
best_oa_location.source.is_in_doaj	True
best_oa_location.source.display_name	Discover Data
best_oa_location.source.host_organization	https://openalex.org/P4310319900
best_oa_location.source.host_organization_name	Springer Science+Business Media
best_oa_location.source.host_organization_lineage	https://openalex.org/P4310319900, https://openalex.org/P4310319965
best_oa_location.source.host_organization_lineage_names	Springer Science+Business Media, Springer Nature
best_oa_location.license	cc-by-nc-nd
best_oa_location.pdf_url	https://link.springer.com/content/pdf/10.1007/s44248-025-00064-0.pdf
best_oa_location.version	publishedVersion
best_oa_location.raw_type	journal-article
best_oa_location.license_id	https://openalex.org/licenses/cc-by-nc-nd
best_oa_location.is_accepted	True
best_oa_location.is_published	True
best_oa_location.raw_source_name	Discover Data
best_oa_location.landing_page_url	https://doi.org/10.1007/s44248-025-00064-0
primary_location.id	doi:10.1007/s44248-025-00064-0
primary_location.is_oa	True
primary_location.source.id	https://openalex.org/S4387287783
primary_location.source.issn	2731-6955
primary_location.source.type	journal
primary_location.source.is_oa	True
primary_location.source.issn_l	2731-6955
primary_location.source.is_core	True
primary_location.source.is_in_doaj	True
primary_location.source.display_name	Discover Data
primary_location.source.host_organization	https://openalex.org/P4310319900
primary_location.source.host_organization_name	Springer Science+Business Media
primary_location.source.host_organization_lineage	https://openalex.org/P4310319900, https://openalex.org/P4310319965
primary_location.source.host_organization_lineage_names	Springer Science+Business Media, Springer Nature
primary_location.license	cc-by-nc-nd
primary_location.pdf_url	https://link.springer.com/content/pdf/10.1007/s44248-025-00064-0.pdf
primary_location.version	publishedVersion
primary_location.raw_type	journal-article
primary_location.license_id	https://openalex.org/licenses/cc-by-nc-nd
primary_location.is_accepted	True
primary_location.is_published	True
primary_location.raw_source_name	Discover Data
primary_location.landing_page_url	https://doi.org/10.1007/s44248-025-00064-0
publication_date	2025-07-01
publication_year	2025
referenced_works	https://openalex.org/W2970641574, https://openalex.org/W4386566925, https://openalex.org/W4225426739, https://openalex.org/W3083510345, https://openalex.org/W2589114814, https://openalex.org/W4386811916, https://openalex.org/W4315491066, https://openalex.org/W4287185050, https://openalex.org/W4384934896, https://openalex.org/W2148143831, https://openalex.org/W2540642777, https://openalex.org/W4411091041, https://openalex.org/W2511234952, https://openalex.org/W2471991522, https://openalex.org/W3175345251, https://openalex.org/W3200253633, https://openalex.org/W4292212771, https://openalex.org/W4226428110, https://openalex.org/W2117190680, https://openalex.org/W2966679659, https://openalex.org/W2756182389, https://openalex.org/W2981515171, https://openalex.org/W3175414601, https://openalex.org/W3000722911, https://openalex.org/W2157364932, https://openalex.org/W2138621090, https://openalex.org/W3035324702, https://openalex.org/W4386212336, https://openalex.org/W4312421335, https://openalex.org/W4285678567, https://openalex.org/W4310733672, https://openalex.org/W3184776482, https://openalex.org/W3156636935, https://openalex.org/W4385570168, https://openalex.org/W4246183800, https://openalex.org/W1493526108, https://openalex.org/W2129250947, https://openalex.org/W2129104434, https://openalex.org/W3174223793, https://openalex.org/W3208862453, https://openalex.org/W2036166268, https://openalex.org/W4287887967, https://openalex.org/W4239510810, https://openalex.org/W4220717373, https://openalex.org/W3099702946
referenced_works_count	45
abstract_inverted_index.a	10, 34, 41, 99, 133, 139
abstract_inverted_index.In	53
abstract_inverted_index.an	119
abstract_inverted_index.as	50
abstract_inverted_index.in	14, 37, 94, 136
abstract_inverted_index.of	4, 105, 122, 142
abstract_inverted_index.to	43, 113
abstract_inverted_index.we	56
abstract_inverted_index.The	1
abstract_inverted_index.and	16, 19, 109, 124
abstract_inverted_index.can	67
abstract_inverted_index.our	85, 130
abstract_inverted_index.set	121
abstract_inverted_index.the	78, 95, 103, 106, 110
abstract_inverted_index.data	6
abstract_inverted_index.deep	125
abstract_inverted_index.loss	89
abstract_inverted_index.make	7
abstract_inverted_index.show	57
abstract_inverted_index.such	49
abstract_inverted_index.text	5, 31, 71, 81, 143
abstract_inverted_index.than	77
abstract_inverted_index.that	58
abstract_inverted_index.they	26
abstract_inverted_index.this	54
abstract_inverted_index.wide	140
abstract_inverted_index.with	29, 46, 64, 90, 118
abstract_inverted_index.based	127
abstract_inverted_index.class	51, 92
abstract_inverted_index.other	79
abstract_inverted_index.still	27
abstract_inverted_index.tasks	9
abstract_inverted_index.across	138
abstract_inverted_index.better	75, 100
abstract_inverted_index.common	35
abstract_inverted_index.paper,	55
abstract_inverted_index.space,	97
abstract_inverted_index.strong	80
abstract_inverted_index.tackle	69
abstract_inverted_index.tasks,	33, 73
abstract_inverted_index.unique	2
abstract_inverted_index.ability	112
abstract_inverted_index.balance	101
abstract_inverted_index.between	102
abstract_inverted_index.complex	11
abstract_inverted_index.models.	83
abstract_inverted_index.notable	134
abstract_inverted_index.produce	44
abstract_inverted_index.several	23
abstract_inverted_index.variety	141
abstract_inverted_index.Abstract	0
abstract_inverted_index.Advances	13
abstract_inverted_index.Compared	117
abstract_inverted_index.However,	25
abstract_inverted_index.allowing	98
abstract_inverted_index.classes.	116
abstract_inverted_index.combined	63
abstract_inverted_index.combines	87
abstract_inverted_index.increase	135
abstract_inverted_index.learning	18, 126
abstract_inverted_index.methods,	129
abstract_inverted_index.overlap.	52
abstract_inverted_index.problem.	12
abstract_inverted_index.proposal	86, 131
abstract_inverted_index.scenario	36
abstract_inverted_index.separate	114
abstract_inverted_index.struggle	28
abstract_inverted_index.tendency	42
abstract_inverted_index.achieving	74
abstract_inverted_index.addressed	22
abstract_inverted_index.competing	128
abstract_inverted_index.datasets.	144
abstract_inverted_index.denoising	65
abstract_inverted_index.different	115
abstract_inverted_index.embedding	96
abstract_inverted_index.extensive	120
abstract_inverted_index.generated	107
abstract_inverted_index.model’s	111
abstract_inverted_index.embeddings	45, 108
abstract_inverted_index.imbalanced	30, 70
abstract_inverted_index.leveraging	59
abstract_inverted_index.real-world	38
abstract_inverted_index.separation	93
abstract_inverted_index.Concretely,	84
abstract_inverted_index.autoencoder	20
abstract_inverted_index.challenges.	24
abstract_inverted_index.class-aware	60
abstract_inverted_index.contrastive	61, 91
abstract_inverted_index.performance	76, 137
abstract_inverted_index.properties,	48
abstract_inverted_index.traditional	123
abstract_inverted_index.unfavorable	47
abstract_inverted_index.autoencoders	66
abstract_inverted_index.demonstrates	132
abstract_inverted_index.optimization	62
abstract_inverted_index.successfully	68
abstract_inverted_index.truthfulness	104
abstract_inverted_index.unsupervised	15
abstract_inverted_index.applications,	39
abstract_inverted_index.architectures	21
abstract_inverted_index.demonstrating	40
abstract_inverted_index.classification	8, 32, 72, 82
abstract_inverted_index.reconstruction	88
abstract_inverted_index.characteristics	3
abstract_inverted_index.semi-supervised	17
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	4
sustainable_development_goals[0].id	https://metadata.un.org/sdg/4
sustainable_development_goals[0].score	0.47999998927116394
sustainable_development_goals[0].display_name	Quality Education
citation_normalized_percentile.value	0.11414956
citation_normalized_percentile.is_in_top_1_percent	False
citation_normalized_percentile.is_in_top_10_percent	True