{"id":"https://openalex.org/W4398192027","doi":"https://doi.org/10.1145/3774904.3792237","title":"Simple-Sampling and Hard-Mixup with Prototypes to Rebalance Contrastive Learning for Text Classification","display_name":"Simple-Sampling and Hard-Mixup with Prototypes to Rebalance Contrastive Learning for Text Classification","publication_year":2026,"publication_date":"2026-04-12","ids":{"openalex":"https://openalex.org/W4398192027","doi":"https://doi.org/10.1145/3774904.3792237"},"language":"en","primary_location":{"id":"doi:10.1145/3774904.3792237","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3774904.3792237","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2405.11524","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100722830","display_name":"Mengyu Li","orcid":"https://orcid.org/0000-0001-9327-434X"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]},{"id":"https://openalex.org/I4210134929","display_name":"Jilin Province Science and Technology Department","ror":"https://ror.org/049x38272","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210134929"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengyu Li","raw_affiliation_strings":["College of Computer Science and Technology, Jilin University, Changchun, China"],"raw_orcid":"https://orcid.org/0000-0001-9327-434X","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Jilin University, Changchun, China","institution_ids":["https://openalex.org/I4210134929","https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101599383","display_name":"Yonghao Liu","orcid":"https://orcid.org/0000-0001-8621-7144"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]},{"id":"https://openalex.org/I4210134929","display_name":"Jilin Province Science and Technology Department","ror":"https://ror.org/049x38272","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210134929"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yonghao Liu","raw_affiliation_strings":["College of Computer Science and Technology, Jilin University, Changchun, China"],"raw_orcid":"https://orcid.org/0000-0001-8621-7144","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Jilin University, Changchun, China","institution_ids":["https://openalex.org/I4210134929","https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001227032","display_name":"Fausto Giunchiglia","orcid":"https://orcid.org/0000-0002-5903-6150"},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Fausto Giunchiglia","raw_affiliation_strings":["Department of Information Engineering and Computer Science, University of Trento, Trento, Italy"],"raw_orcid":"https://orcid.org/0000-0002-5903-6150","affiliations":[{"raw_affiliation_string":"Department of Information Engineering and Computer Science, University of Trento, Trento, Italy","institution_ids":["https://openalex.org/I193223587"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ximing Li","orcid":"https://orcid.org/0000-0001-8190-5087"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]},{"id":"https://openalex.org/I4210134929","display_name":"Jilin Province Science and Technology Department","ror":"https://ror.org/049x38272","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210134929"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ximing Li","raw_affiliation_strings":["College of Computer Science and Technology, Jilin University, Changchun, China"],"raw_orcid":"https://orcid.org/0000-0001-8190-5087","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Jilin University, Changchun, China","institution_ids":["https://openalex.org/I4210134929","https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052831869","display_name":"Xiaoyue Feng","orcid":"https://orcid.org/0000-0003-3954-1333"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]},{"id":"https://openalex.org/I4210134929","display_name":"Jilin Province Science and Technology Department","ror":"https://ror.org/049x38272","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210134929"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyue Feng","raw_affiliation_strings":["College of Computer Science and Technology, Jilin University, Changchun, China"],"raw_orcid":"https://orcid.org/0000-0003-3954-1333","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Jilin University, Changchun, China","institution_ids":["https://openalex.org/I4210134929","https://openalex.org/I194450716"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007914848","display_name":"Renchu Guan","orcid":"https://orcid.org/0000-0002-7162-7826"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]},{"id":"https://openalex.org/I4210134929","display_name":"Jilin Province Science and Technology Department","ror":"https://ror.org/049x38272","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210134929"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Renchu Guan","raw_affiliation_strings":["College of Computer Science and Technology, Jilin University, Changchun, China"],"raw_orcid":"https://orcid.org/0000-0002-7162-7826","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Jilin University, Changchun, China","institution_ids":["https://openalex.org/I4210134929","https://openalex.org/I194450716"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3698","last_page":"3708"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9563999772071838,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9563999772071838,"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/simple","display_name":"Simple (philosophy)","score":0.8124494552612305},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6407429575920105},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5832219123840332},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.514714777469635},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44139623641967773},{"id":"https://openalex.org/keywords/simple-random-sample","display_name":"Simple random sample","score":0.43332237005233765},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.372689813375473},{"id":"https://openalex.org/keywords/sociology","display_name":"Sociology","score":0.13787966966629028},{"id":"https://openalex.org/keywords/epistemology","display_name":"Epistemology","score":0.07241111993789673},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07155314087867737}],"concepts":[{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.8124494552612305},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6407429575920105},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5832219123840332},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.514714777469635},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44139623641967773},{"id":"https://openalex.org/C20353970","wikidata":"https://www.wikidata.org/wiki/Q1056998","display_name":"Simple random sample","level":3,"score":0.43332237005233765},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.372689813375473},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.13787966966629028},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.07241111993789673},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07155314087867737},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3774904.3792237","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3774904.3792237","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2405.11524","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.11524","pdf_url":"https://arxiv.org/pdf/2405.11524","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2405.11524","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2405.11524","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2405.11524","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.11524","pdf_url":"https://arxiv.org/pdf/2405.11524","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4398192027.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2370014976","https://openalex.org/W2350399852","https://openalex.org/W4238714840","https://openalex.org/W3047864323","https://openalex.org/W1036777753","https://openalex.org/W2181928643","https://openalex.org/W4379210352","https://openalex.org/W3004700962","https://openalex.org/W2994963386","https://openalex.org/W2367020632"],"abstract_inverted_index":{"Text":[0],"classification":[1,89,116,130],"is":[2,73,192],"a":[3,108,135,150],"crucial":[4],"and":[5,20,44,65,94,152],"fundamental":[6],"task":[7],"in":[8,127],"web":[9],"content":[10],"mining.":[11],"Compared":[12],"with":[13,91,157],"the":[14,26,66,81,121,128,145,158,166,175],"previous":[15],"learning":[16,31,42,67,72,97,169],"paradigm":[17],"of":[18,69,124,137,177],"pre-training":[19],"fine-tuning":[21],"by":[22,141],"cross":[23,92],"entropy":[24,93],"loss,":[25],"recently":[27],"proposed":[28],"supervised":[29,70,95,167],"contrastive":[30,71,96,168],"approach":[32],"has":[33],"received":[34],"tremendous":[35],"attention":[36],"due":[37],"to":[38,75,132,164],"its":[39],"powerful":[40],"feature":[41],"capability":[43],"robustness.":[45],"Although":[46],"several":[47,188],"studies":[48],"have":[49],"incorporated":[50],"this":[51,104],"technique":[52],"for":[53,113,161],"text":[54,61,115],"classification,":[55],"some":[56],"limitations":[57],"remain.":[58],"First,":[59,118],"many":[60],"datasets":[62],"are":[63],"imbalanced,":[64],"mechanism":[68],"sensitive":[74],"data":[76],"imbalance,":[77],"which":[78,180],"may":[79],"harm":[80],"model's":[82],"performance.":[83],"Moreover,":[84],"these":[85],"models":[86,186],"leverage":[87],"separate":[88],"branches":[90,98],"without":[99],"explicit":[100],"mutual":[101],"guidance.":[102],"To":[103],"end,":[105],"we":[106,119,148],"propose":[107],"novel":[109],"model":[110],"named":[111],"SharpReCL":[112],"imbalanced":[114],"tasks.":[117],"obtain":[120],"prototype":[122,146],"vector":[123],"each":[125,138,162],"class":[126,163],"balanced":[129],"branch":[131],"act":[133],"as":[134],"representation":[136],"class.":[139],"Then,":[140],"further":[142],"explicitly":[143],"leveraging":[144],"vectors,":[147],"construct":[149],"proper":[151],"sufficient":[153],"target":[154],"sample":[155],"set":[156],"same":[159],"size":[160],"perform":[165],"procedure.":[170],"The":[171],"empirical":[172],"results":[173],"show":[174],"effectiveness":[176],"our":[178],"model,":[179],"even":[181],"outperforms":[182],"popular":[183],"large":[184],"language":[185],"across":[187],"datasets.":[189],"Our":[190],"code":[191],"available":[193],"here.":[194]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2024-05-22T00:00:00"}