{"id":"https://openalex.org/W7154609261","doi":"https://doi.org/10.1007/s11280-026-01415-w","title":"Cluster-SCP: Similarity and Contrastive Learning to Enhance Pseudo Labels for Fine Tuning under Few Labels","display_name":"Cluster-SCP: Similarity and Contrastive Learning to Enhance Pseudo Labels for Fine Tuning under Few Labels","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7154609261","doi":"https://doi.org/10.1007/s11280-026-01415-w"},"language":"en","primary_location":{"id":"doi:10.1007/s11280-026-01415-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11280-026-01415-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11280-026-01415-w.pdf","source":{"id":"https://openalex.org/S129236917","display_name":"World Wide Web","issn_l":"1386-145X","issn":["1386-145X","1573-1413"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"World Wide Web","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11280-026-01415-w.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103212907","display_name":"Abdullah Alsuhaibani","orcid":"https://orcid.org/0000-0003-1595-9225"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]},{"id":"https://openalex.org/I4210151290","display_name":"Islamic University of Madinah","ror":"https://ror.org/03rcp1y74","country_code":"SA","type":"education","lineage":["https://openalex.org/I4210151290"]}],"countries":["AU","SA"],"is_corresponding":false,"raw_author_name":"Abdullah Alsuhaibani","raw_affiliation_strings":["Islamic University of Madinah, Medina, Saudi Arabia","University of Technology Sydney, Sydney, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Islamic University of Madinah, Medina, Saudi Arabia","institution_ids":["https://openalex.org/I4210151290"]},{"raw_affiliation_string":"University of Technology Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062919638","display_name":"Abdulrahman Alalawi","orcid":null},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Abdulrahman Alalawi","raw_affiliation_strings":["The University of New South Wales, Sydney, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133806072","display_name":"Imran Razzak","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Imran Razzak","raw_affiliation_strings":["MBZUAI, Abu Dhabi, United Arab Emirates"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MBZUAI, Abu Dhabi, United Arab Emirates","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133794009","display_name":"Shoaib Jameel","orcid":null},"institutions":[{"id":"https://openalex.org/I43439940","display_name":"University of Southampton","ror":"https://ror.org/01ryk1543","country_code":"GB","type":"education","lineage":["https://openalex.org/I43439940"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Shoaib Jameel","raw_affiliation_strings":["University of Southampton, Southampton, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southampton, Southampton, UK","institution_ids":["https://openalex.org/I43439940"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076107706","display_name":"Xianzhi Wang","orcid":"https://orcid.org/0000-0001-9582-3445"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xianzhi Wang","raw_affiliation_strings":["University of Technology Sydney, Sydney, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Technology Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5133745098","display_name":"Guandong Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]},{"id":"https://openalex.org/I4210086892","display_name":"Education University of Hong Kong","ror":"https://ror.org/000t0f062","country_code":"HK","type":"education","lineage":["https://openalex.org/I4210086892"]}],"countries":["AU","HK"],"is_corresponding":true,"raw_author_name":"Guandong Xu","raw_affiliation_strings":["The Education University of Hong Kong, HK, Hong Kong","University of Technology Sydney, Sydney, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Education University of Hong Kong, HK, Hong Kong","institution_ids":["https://openalex.org/I4210086892"]},{"raw_affiliation_string":"University of Technology Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]}],"institutions":[],"countries_distinct_count":5,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5133745098"],"corresponding_institution_ids":["https://openalex.org/I114017466","https://openalex.org/I4210086892"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":{"value":2990,"currency":"USD","value_usd":2990},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.46636901,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"29","issue":"3","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.2721000015735626,"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/T10028","display_name":"Topic Modeling","score":0.2721000015735626,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.25619998574256897,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.12110000103712082,"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/initialization","display_name":"Initialization","score":0.7627000212669373},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7105000019073486},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.676800012588501},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5501999855041504},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4884999990463257},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"Fine-tuning","score":0.4749999940395355},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.46070000529289246},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4318999946117401}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8745999932289124},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.7627000212669373},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7105000019073486},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.676800012588501},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6154999732971191},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5501999855041504},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4884999990463257},{"id":"https://openalex.org/C157524613","wikidata":"https://www.wikidata.org/wiki/Q2828883","display_name":"Fine-tuning","level":2,"score":0.4749999940395355},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.46070000529289246},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4318999946117401},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4187999963760376},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.39320001006126404},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.38609999418258667},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3449000120162964},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.3361000120639801},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.3262999951839447},{"id":"https://openalex.org/C105611402","wikidata":"https://www.wikidata.org/wiki/Q2976589","display_name":"Spectral clustering","level":3,"score":0.313400000333786},{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.30399999022483826},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.29820001125335693},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.2980000078678131},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2953999936580658},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.27399998903274536},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.25699999928474426}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11280-026-01415-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11280-026-01415-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11280-026-01415-w.pdf","source":{"id":"https://openalex.org/S129236917","display_name":"World Wide Web","issn_l":"1386-145X","issn":["1386-145X","1573-1413"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"World Wide Web","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s11280-026-01415-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11280-026-01415-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11280-026-01415-w.pdf","source":{"id":"https://openalex.org/S129236917","display_name":"World Wide Web","issn_l":"1386-145X","issn":["1386-145X","1573-1413"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"World Wide Web","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2729752981","display_name":"\u57fa\u4e8e\u56e0\u679c\u5206\u6790\u7684\u53ef\u89e3\u91ca\u63a8\u8350\u7cfb\u7edf\u7684\u7b97\u6cd5\u7406\u8bba\u4e0e\u5e94\u7528\u7814\u7a76","funder_award_id":"62072257","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G761888125","display_name":null,"funder_award_id":"LE220100078","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320967","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7154609261.pdf","grobid_xml":"https://content.openalex.org/works/W7154609261.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W1479807131","https://openalex.org/W1977556410","https://openalex.org/W2035979693","https://openalex.org/W2099006396","https://openalex.org/W2730106296","https://openalex.org/W2883725317","https://openalex.org/W2948196881","https://openalex.org/W2963341956","https://openalex.org/W2969521304","https://openalex.org/W2970641574","https://openalex.org/W2981059842","https://openalex.org/W3004946360","https://openalex.org/W3019913914","https://openalex.org/W3035524453","https://openalex.org/W3035568641","https://openalex.org/W3035602763","https://openalex.org/W3156636935","https://openalex.org/W3171153522","https://openalex.org/W3176382883","https://openalex.org/W3198507920","https://openalex.org/W3209810427","https://openalex.org/W4206206673","https://openalex.org/W4225385501","https://openalex.org/W4283800530","https://openalex.org/W4284680079","https://openalex.org/W4284702000","https://openalex.org/W4285206744","https://openalex.org/W4385570670","https://openalex.org/W4385572233","https://openalex.org/W4385574373","https://openalex.org/W4388194748","https://openalex.org/W4390990571","https://openalex.org/W4392384725","https://openalex.org/W4402671988","https://openalex.org/W4404724815"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Language":[1],"models":[2],"often":[3],"underperform":[4],"when":[5],"fine":[6,37,117],"tuned":[7],"with":[8,30,78,106],"limited":[9],"labelled":[10,34],"data.":[11],"To":[12],"reduce":[13],"dependence":[14],"on":[15,132],"costly":[16],"annotation,":[17],"recent":[18],"studies":[19],"have":[20],"explored":[21],"clustering":[22,45,98],"and":[23,47,65,81,100,142],"pseudo":[24,73,111],"labelling":[25],"to":[26,69,96,116],"leverage":[27],"unlabeled":[28],"text":[29],"only":[31],"a":[32,58,126,148],"few":[33],"examples":[35],"for":[36],"tuning.":[38],"However,":[39],"these":[40],"methods":[41],"face":[42],"persistent":[43],"challenges:":[44],"errors":[46],"pseudo-label":[48],"mismatches":[49],"can":[50],"degrade":[51],"fine-tuning":[52],"performance.":[53],"We":[54],"propose":[55],"Cluster-SCP":[56,138],",":[57,90],"novel":[59],"framework":[60,76],"that":[61,137],"improves":[62],"intra-cluster":[63],"coherence":[64],"reduces":[66],"cluster":[67,101],"quantity":[68],"generate":[70],"more":[71],"reliable":[72],"labels.":[74,130],"The":[75,109],"begins":[77],"K-Means":[79],"initialization":[80],"applies":[82],"an":[83],"iterative":[84],"refinement":[85],"process,":[86],"Intermediate":[87],"Pseudo":[88],"Labels":[89],"comprising":[91],"two":[92],"stages:":[93],"embedding":[94],"reassignment":[95],"minimize":[97],"errors,":[99],"merging":[102],"via":[103],"contrastive":[104],"learning":[105],"graph":[107],"readouts.":[108],"refined":[110,124],"labels":[112],"are":[113],"first":[114],"used":[115],"tune":[118],"language":[119],"model,":[120],"which":[121],"is":[122],"subsequently":[123],"using":[125],"small":[127],"set":[128],"of":[129,156],"Experiments":[131],"three":[133],"benchmark":[134],"datasets":[135],"show":[136],"consistently":[139],"outperforms":[140],"baseline":[141],"state-of-the-art":[143],"methods,":[144],"achieving":[145],"at":[146],"least":[147],"5.3%":[149],"accuracy":[150],"improvement":[151],"while":[152],"reducing":[153],"the":[154],"number":[155],"clusters":[157],"by":[158],"22%.":[159]},"counts_by_year":[],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2026-04-17T00:00:00"}