Robust Partial-Label Learning by Leveraging Class Activation Values Article Swipe

PDF

YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2502.11743

Real-world training data is often noisy; for example, human annotators assign conflicting class labels to the same instances. Partial-label learning (PLL) is a weakly supervised learning paradigm that allows training classifiers in this context without manual data cleaning. While state-of-the-art methods have good predictive performance, their predictions are sensitive to high noise levels, out-of-distribution data, and adversarial perturbations. We propose a novel PLL method based on subjective logic, which explicitly represents uncertainty by leveraging the magnitudes of the underlying neural network's class activation values. Thereby, we effectively incorporate prior knowledge about the class labels by using a novel label weight re-distribution strategy that we prove to be optimal. We empirically show that our method yields more robust predictions in terms of predictive performance under high PLL noise levels, handling out-of-distribution examples, and handling adversarial perturbations on the test instances.

Related Topics

Computer Science

Artificial Intelligence

Business

Concepts

Class (philosophy) Computer science Artificial intelligence Business

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2502.11743
PDF: https://arxiv.org/pdf/2502.11743
OA Status: green
Related Works: 10
OpenAlex ID: https://openalex.org/W4407719609

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4407719609

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2502.11743

Digital Object Identifier
Title: Robust Partial-Label Learning by Leveraging Class Activation Values

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2025

Year of publication
Publication date: 2025-02-17

Full publication date if available
Authors: Tobias A. Fuchs, Florian Kalinke

List of authors in order
Landing page: https://arxiv.org/abs/2502.11743

Publisher landing page
PDF URL: https://arxiv.org/pdf/2502.11743

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/2502.11743

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

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

Total citation count in OpenAlex
Related works (count): 10

Other works algorithmically related by OpenAlex

Full payload

id	https://openalex.org/W4407719609
doi	https://doi.org/10.48550/arxiv.2502.11743
ids.doi	https://doi.org/10.48550/arxiv.2502.11743
ids.openalex	https://openalex.org/W4407719609
fwci
type	preprint
title	Robust Partial-Label Learning by Leveraging Class Activation Values
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
topics[0].id	https://openalex.org/T11550
topics[0].field.id	https://openalex.org/fields/17
topics[0].field.display_name	Computer Science
topics[0].score	0.9221000075340271
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	Text and Document Classification Technologies
is_xpac	False
apc_list
apc_paid
concepts[0].id	https://openalex.org/C2777212361
concepts[0].level	2
concepts[0].score	0.6513568162918091
concepts[0].wikidata	https://www.wikidata.org/wiki/Q5127848
concepts[0].display_name	Class (philosophy)
concepts[1].id	https://openalex.org/C41008148
concepts[1].level	0
concepts[1].score	0.4505338668823242
concepts[1].wikidata	https://www.wikidata.org/wiki/Q21198
concepts[1].display_name	Computer science
concepts[2].id	https://openalex.org/C154945302
concepts[2].level	1
concepts[2].score	0.3727870583534241
concepts[2].wikidata	https://www.wikidata.org/wiki/Q11660
concepts[2].display_name	Artificial intelligence
concepts[3].id	https://openalex.org/C144133560
concepts[3].level	0
concepts[3].score	0.33127036690711975
concepts[3].wikidata	https://www.wikidata.org/wiki/Q4830453
concepts[3].display_name	Business
keywords[0].id	https://openalex.org/keywords/class
keywords[0].score	0.6513568162918091
keywords[0].display_name	Class (philosophy)
keywords[1].id	https://openalex.org/keywords/computer-science
keywords[1].score	0.4505338668823242
keywords[1].display_name	Computer science
keywords[2].id	https://openalex.org/keywords/artificial-intelligence
keywords[2].score	0.3727870583534241
keywords[2].display_name	Artificial intelligence
keywords[3].id	https://openalex.org/keywords/business
keywords[3].score	0.33127036690711975
keywords[3].display_name	Business
language	en
locations[0].id	pmh:oai:arXiv.org:2502.11743
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/2502.11743
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/2502.11743
locations[1].id	doi:10.48550/arxiv.2502.11743
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	cc-by
locations[1].pdf_url
locations[1].version
locations[1].raw_type	article
locations[1].license_id	https://openalex.org/licenses/cc-by
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.2502.11743
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5013911322
authorships[0].author.orcid	https://orcid.org/0000-0001-8812-9359
authorships[0].author.display_name	Tobias A. Fuchs
authorships[0].author_position	first
authorships[0].raw_author_name	Fuchs, Tobias
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5054748088
authorships[1].author.orcid	https://orcid.org/0000-0002-0443-6288
authorships[1].author.display_name	Florian Kalinke
authorships[1].author_position	last
authorships[1].raw_author_name	Kalinke, Florian
authorships[1].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/2502.11743
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	Robust Partial-Label Learning by Leveraging Class Activation Values
has_fulltext	False
is_retracted	False
updated_date	2025-11-06T06:51:31.235846
primary_topic.id	https://openalex.org/T11550
primary_topic.field.id	https://openalex.org/fields/17
primary_topic.field.display_name	Computer Science
primary_topic.score	0.9221000075340271
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	Text and Document Classification Technologies
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/W4396696052
cited_by_count	0
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2502.11743
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/2502.11743
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/2502.11743
primary_location.id	pmh:oai:arXiv.org:2502.11743
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/2502.11743
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/2502.11743
publication_date	2025-02-17
publication_year	2025
referenced_works_count	0
abstract_inverted_index.a	22, 60, 96
abstract_inverted_index.We	58, 108
abstract_inverted_index.be	106
abstract_inverted_index.by	72, 94
abstract_inverted_index.in	31, 118
abstract_inverted_index.is	3, 21
abstract_inverted_index.of	76, 120
abstract_inverted_index.on	65, 135
abstract_inverted_index.to	14, 49, 105
abstract_inverted_index.we	85, 103
abstract_inverted_index.PLL	62, 125
abstract_inverted_index.and	55, 131
abstract_inverted_index.are	47
abstract_inverted_index.for	6
abstract_inverted_index.our	112
abstract_inverted_index.the	15, 74, 77, 91, 136
abstract_inverted_index.data	2, 36
abstract_inverted_index.good	42
abstract_inverted_index.have	41
abstract_inverted_index.high	50, 124
abstract_inverted_index.more	115
abstract_inverted_index.same	16
abstract_inverted_index.show	110
abstract_inverted_index.test	137
abstract_inverted_index.that	27, 102, 111
abstract_inverted_index.this	32
abstract_inverted_index.(PLL)	20
abstract_inverted_index.While	38
abstract_inverted_index.about	90
abstract_inverted_index.based	64
abstract_inverted_index.class	12, 81, 92
abstract_inverted_index.data,	54
abstract_inverted_index.human	8
abstract_inverted_index.label	98
abstract_inverted_index.noise	51, 126
abstract_inverted_index.novel	61, 97
abstract_inverted_index.often	4
abstract_inverted_index.prior	88
abstract_inverted_index.prove	104
abstract_inverted_index.terms	119
abstract_inverted_index.their	45
abstract_inverted_index.under	123
abstract_inverted_index.using	95
abstract_inverted_index.which	68
abstract_inverted_index.allows	28
abstract_inverted_index.assign	10
abstract_inverted_index.labels	13, 93
abstract_inverted_index.logic,	67
abstract_inverted_index.manual	35
abstract_inverted_index.method	63, 113
abstract_inverted_index.neural	79
abstract_inverted_index.noisy;	5
abstract_inverted_index.robust	116
abstract_inverted_index.weakly	23
abstract_inverted_index.weight	99
abstract_inverted_index.yields	114
abstract_inverted_index.context	33
abstract_inverted_index.levels,	52, 127
abstract_inverted_index.methods	40
abstract_inverted_index.propose	59
abstract_inverted_index.values.	83
abstract_inverted_index.without	34
abstract_inverted_index.Thereby,	84
abstract_inverted_index.example,	7
abstract_inverted_index.handling	128, 132
abstract_inverted_index.learning	19, 25
abstract_inverted_index.optimal.	107
abstract_inverted_index.paradigm	26
abstract_inverted_index.strategy	101
abstract_inverted_index.training	1, 29
abstract_inverted_index.cleaning.	37
abstract_inverted_index.examples,	130
abstract_inverted_index.knowledge	89
abstract_inverted_index.network's	80
abstract_inverted_index.sensitive	48
abstract_inverted_index.Real-world	0
abstract_inverted_index.activation	82
abstract_inverted_index.annotators	9
abstract_inverted_index.explicitly	69
abstract_inverted_index.instances.	17, 138
abstract_inverted_index.leveraging	73
abstract_inverted_index.magnitudes	75
abstract_inverted_index.predictive	43, 121
abstract_inverted_index.represents	70
abstract_inverted_index.subjective	66
abstract_inverted_index.supervised	24
abstract_inverted_index.underlying	78
abstract_inverted_index.adversarial	56, 133
abstract_inverted_index.classifiers	30
abstract_inverted_index.conflicting	11
abstract_inverted_index.effectively	86
abstract_inverted_index.empirically	109
abstract_inverted_index.incorporate	87
abstract_inverted_index.performance	122
abstract_inverted_index.predictions	46, 117
abstract_inverted_index.uncertainty	71
abstract_inverted_index.performance,	44
abstract_inverted_index.Partial-label	18
abstract_inverted_index.perturbations	134
abstract_inverted_index.perturbations.	57
abstract_inverted_index.re-distribution	100
abstract_inverted_index.state-of-the-art	39
abstract_inverted_index.out-of-distribution	53, 129
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	2
citation_normalized_percentile