{"id":"https://openalex.org/W4415974583","doi":"https://doi.org/10.1016/j.procs.2025.09.214","title":"Categorical Pseudo-Labeling with Iterative Cluster Expansion","display_name":"Categorical Pseudo-Labeling with Iterative Cluster Expansion","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4415974583","doi":"https://doi.org/10.1016/j.procs.2025.09.214"},"language":"en","primary_location":{"id":"doi:10.1016/j.procs.2025.09.214","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.procs.2025.09.214","pdf_url":null,"source":{"id":"https://openalex.org/S120348307","display_name":"Procedia Computer Science","issn_l":"1877-0509","issn":["1877-0509"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Procedia Computer Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1016/j.procs.2025.09.214","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044243080","display_name":"Weronika \u0141azarz","orcid":null},"institutions":[{"id":"https://openalex.org/I864159182","display_name":"University of Silesia in Katowice","ror":"https://ror.org/0104rcc94","country_code":"PL","type":"education","lineage":["https://openalex.org/I864159182"]}],"countries":["PL"],"is_corresponding":true,"raw_author_name":"Weronika \u0141azarz","raw_affiliation_strings":["Institute of Computer Science, University of Silesia, Bankowa 12, Katowice 40-007, Poland"],"affiliations":[{"raw_affiliation_string":"Institute of Computer Science, University of Silesia, Bankowa 12, Katowice 40-007, Poland","institution_ids":["https://openalex.org/I864159182"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088457184","display_name":"Agnieszka Nowak-Brzezi\u0144ska","orcid":"https://orcid.org/0000-0001-7238-1170"},"institutions":[{"id":"https://openalex.org/I864159182","display_name":"University of Silesia in Katowice","ror":"https://ror.org/0104rcc94","country_code":"PL","type":"education","lineage":["https://openalex.org/I864159182"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Agnieszka Nowak-Brzezi\u0144ska","raw_affiliation_strings":["Institute of Computer Science, University of Silesia, Bankowa 12, Katowice 40-007, Poland"],"affiliations":[{"raw_affiliation_string":"Institute of Computer Science, University of Silesia, Bankowa 12, Katowice 40-007, Poland","institution_ids":["https://openalex.org/I864159182"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5044243080"],"corresponding_institution_ids":["https://openalex.org/I864159182"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18192382,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"270","issue":null,"first_page":"937","last_page":"946"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.17309999465942383,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.17309999465942383,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.1429000049829483,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.06480000168085098,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.8966000080108643},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.582099974155426},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5221999883651733},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5044999718666077},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.47600001096725464},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.4142000079154968},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.40400001406669617},{"id":"https://openalex.org/keywords/iterative-refinement","display_name":"Iterative refinement","score":0.376800000667572}],"concepts":[{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.8966000080108643},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8385000228881836},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.582099974155426},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5221999883651733},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.510200023651123},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5044999718666077},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4837999939918518},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.47600001096725464},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4740000069141388},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.4142000079154968},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.40400001406669617},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.376800000667572},{"id":"https://openalex.org/C117619785","wikidata":"https://www.wikidata.org/wiki/Q6094414","display_name":"Iterative learning control","level":3,"score":0.3727000057697296},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.34709998965263367},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3402000069618225},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.33329999446868896},{"id":"https://openalex.org/C21080849","wikidata":"https://www.wikidata.org/wiki/Q13611879","display_name":"Data point","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C60044698","wikidata":"https://www.wikidata.org/wiki/Q1283324","display_name":"Refining (metallurgy)","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25440001487731934}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.procs.2025.09.214","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.procs.2025.09.214","pdf_url":null,"source":{"id":"https://openalex.org/S120348307","display_name":"Procedia Computer Science","issn_l":"1877-0509","issn":["1877-0509"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Procedia Computer Science","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.procs.2025.09.214","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.procs.2025.09.214","pdf_url":null,"source":{"id":"https://openalex.org/S120348307","display_name":"Procedia Computer Science","issn_l":"1877-0509","issn":["1877-0509"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Procedia Computer Science","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1523439439","https://openalex.org/W1678356000","https://openalex.org/W1817561967","https://openalex.org/W1930624869","https://openalex.org/W1980073965","https://openalex.org/W1984116161","https://openalex.org/W1987971958","https://openalex.org/W1988790447","https://openalex.org/W1991530504","https://openalex.org/W2029064186","https://openalex.org/W2051224630","https://openalex.org/W2147962921","https://openalex.org/W2149706766","https://openalex.org/W2740924709","https://openalex.org/W4285098504","https://openalex.org/W4388714381","https://openalex.org/W4404835105"],"related_works":[],"abstract_inverted_index":{"Labeling":[0],"categorical":[1,56,150],"data":[2,89,127,151],"is":[3,14,131,152],"a":[4,70,121],"critical":[5],"challenge":[6],"in":[7,117],"many":[8],"real-world":[9,135],"applications":[10],"where":[11,146],"expert":[12],"annotation":[13],"costly,":[15],"time-consuming,":[16],"and":[17,143],"often":[18,23],"impractical.":[19],"Moreover,":[20],"we":[21,61],"very":[22],"face":[24],"the":[25,52],"problem":[26],"of":[27,55,149],"training":[28],"sets":[29],"that":[30,74,111],"are":[31],"too":[32],"small":[33],"or":[34],"unrepresentative":[35],"to":[36,50,79],"apply":[37],"supervised":[38],"learning":[39],"techniques.":[40],"Traditional":[41],"pseudo-labeling":[42],"techniques,":[43],"primarily":[44],"designed":[45],"for":[46,125,134,154],"numerical":[47],"data,":[48],"struggle":[49],"handle":[51],"unique":[53],"characteristics":[54],"datasets.":[57,83],"To":[58],"address":[59],"this,":[60],"introduce":[62],"Categorical":[63],"Pseudo-Labeling":[64],"with":[65],"Iterative":[66],"Cluster":[67],"Expansion":[68],"(CPLICE),":[69],"novel":[71],"clustering-based":[72],"approach":[73],"leverages":[75],"qualitative":[76],"similarity":[77],"measures":[78],"iteratively":[80],"expand":[81],"labeled":[82],"Unlike":[84],"probability-based":[85],"pseudo-labeling,":[86],"CPLICE":[87,112],"selects":[88],"points":[90],"based":[91],"on":[92],"their":[93],"distance":[94],"from":[95],"established":[96],"clusters,":[97],"progressively":[98],"refining":[99],"labels":[100],"while":[101],"handling":[102,148],"ambiguous":[103],"cases":[104],"through":[105],"dynamic":[106],"reassignments.":[107],"Our":[108],"results":[109],"demonstrate":[110],"outperforms":[113],"traditional":[114],"tree-based":[115],"models":[116],"low-label":[118],"environments,":[119],"providing":[120],"stable,":[122],"scalable":[123],"solution":[124],"effective":[126],"labeling.":[128],"This":[129],"method":[130],"particularly":[132],"valuable":[133],"scenarios":[136],"such":[137],"as":[138],"medical":[139],"diagnostics,":[140],"customer":[141],"segmentation,":[142],"fraud":[144],"detection,":[145],"robust":[147],"essential":[153],"accurate,":[155],"interpretable":[156],"models.":[157]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-06T00:00:00"}