{"id":"https://openalex.org/W4384639909","doi":"https://doi.org/10.1145/3539618.3591638","title":"An Effective, Efficient, and Scalable Confidence-based Instance Selection Framework for Transformer-Based Text Classification","display_name":"An Effective, Efficient, and Scalable Confidence-based Instance Selection Framework for Transformer-Based Text Classification","publication_year":2023,"publication_date":"2023-07-18","ids":{"openalex":"https://openalex.org/W4384639909","doi":"https://doi.org/10.1145/3539618.3591638"},"language":"en","primary_location":{"id":"doi:10.1145/3539618.3591638","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539618.3591638","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018690278","display_name":"Washington Cunha","orcid":"https://orcid.org/0000-0002-1988-8412"},"institutions":[{"id":"https://openalex.org/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Washington Cunha","raw_affiliation_strings":["Federal University of Minas Gerais, Belo Horizonte, Brazil"],"raw_orcid":"https://orcid.org/0000-0002-1988-8412","affiliations":[{"raw_affiliation_string":"Federal University of Minas Gerais, Belo Horizonte, Brazil","institution_ids":["https://openalex.org/I110200422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082661016","display_name":"Celso Fran\u00e7a","orcid":"https://orcid.org/0000-0002-0251-7172"},"institutions":[{"id":"https://openalex.org/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Celso Fran\u00e7a","raw_affiliation_strings":["Federal University of Minas Gerais, Belo Horizonte, Brazil"],"raw_orcid":"https://orcid.org/0000-0002-0251-7172","affiliations":[{"raw_affiliation_string":"Federal University of Minas Gerais, Belo Horizonte, Brazil","institution_ids":["https://openalex.org/I110200422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070081136","display_name":"Guilherme Fonseca","orcid":"https://orcid.org/0009-0000-7862-8701"},"institutions":[{"id":"https://openalex.org/I166595947","display_name":"Federal University of S\u00e3o Jo\u00e3o del-Rei","ror":"https://ror.org/03vrj4p82","country_code":"BR","type":"education","lineage":["https://openalex.org/I166595947"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Guilherme Fonseca","raw_affiliation_strings":["Federal University of S\u00e3o Jo\u00e3o del Rei, S\u00e3o Jo\u00e3o del Rei, Brazil"],"raw_orcid":"https://orcid.org/0009-0000-7862-8701","affiliations":[{"raw_affiliation_string":"Federal University of S\u00e3o Jo\u00e3o del Rei, S\u00e3o Jo\u00e3o del Rei, Brazil","institution_ids":["https://openalex.org/I166595947"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087565388","display_name":"Leonardo Rocha","orcid":"https://orcid.org/0000-0002-4913-4902"},"institutions":[{"id":"https://openalex.org/I166595947","display_name":"Federal University of S\u00e3o Jo\u00e3o del-Rei","ror":"https://ror.org/03vrj4p82","country_code":"BR","type":"education","lineage":["https://openalex.org/I166595947"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Leonardo Rocha","raw_affiliation_strings":["Federal University of S\u00e3o Jo\u00e3o del Rei, S\u00e3o Jo\u00e3o del Rei, Brazil"],"raw_orcid":"https://orcid.org/0000-0002-4913-4902","affiliations":[{"raw_affiliation_string":"Federal University of S\u00e3o Jo\u00e3o del Rei, S\u00e3o Jo\u00e3o del Rei, Brazil","institution_ids":["https://openalex.org/I166595947"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046370637","display_name":"Marcos Andr\u00e9 Gon\u00e7alves","orcid":"https://orcid.org/0000-0002-2075-3363"},"institutions":[{"id":"https://openalex.org/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Marcos Andr\u00e9 Gon\u00e7alves","raw_affiliation_strings":["Federal University of Minas Gerais, Belo Horizonte, Brazil"],"raw_orcid":"https://orcid.org/0000-0002-2075-3363","affiliations":[{"raw_affiliation_string":"Federal University of Minas Gerais, Belo Horizonte, Brazil","institution_ids":["https://openalex.org/I110200422"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"665","last_page":"674"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9980999827384949,"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":0.9883000254631042,"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/scalability","display_name":"Scalability","score":0.8369102478027344},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8282195329666138},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.7234665155410767},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7158441543579102},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6311379671096802},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.615054190158844},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5792226195335388},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5175718069076538},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.44004929065704346},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.41782116889953613},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.40568646788597107},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.12258392572402954}],"concepts":[{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.8369102478027344},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8282195329666138},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.7234665155410767},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7158441543579102},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6311379671096802},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.615054190158844},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5792226195335388},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5175718069076538},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.44004929065704346},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.41782116889953613},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40568646788597107},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.12258392572402954},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3539618.3591638","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539618.3591638","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320310598","display_name":"Amazon Web Services","ror":"https://ror.org/04mv4n011"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1965551184","https://openalex.org/W1994410331","https://openalex.org/W2015629112","https://openalex.org/W2073241381","https://openalex.org/W2083619974","https://openalex.org/W2107686700","https://openalex.org/W2115012618","https://openalex.org/W2118020653","https://openalex.org/W2151537585","https://openalex.org/W2170505850","https://openalex.org/W2790199850","https://openalex.org/W2797779452","https://openalex.org/W2905417435","https://openalex.org/W2950813464","https://openalex.org/W2954580219","https://openalex.org/W2963023579","https://openalex.org/W2963469388","https://openalex.org/W2963626623","https://openalex.org/W2970597249","https://openalex.org/W3004511681","https://openalex.org/W3022371575","https://openalex.org/W3022945404","https://openalex.org/W3027761037","https://openalex.org/W3034999214","https://openalex.org/W3094560306","https://openalex.org/W3099825604","https://openalex.org/W3126191299","https://openalex.org/W3153906321","https://openalex.org/W3156333129","https://openalex.org/W3164238513","https://openalex.org/W3197834140","https://openalex.org/W3209934390","https://openalex.org/W4210374324","https://openalex.org/W4213421478","https://openalex.org/W4284963545","https://openalex.org/W4288280764","https://openalex.org/W4317904898","https://openalex.org/W4365459368","https://openalex.org/W6793983436"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W17155033","https://openalex.org/W2150291671","https://openalex.org/W2013643406","https://openalex.org/W2027972911","https://openalex.org/W2157978810","https://openalex.org/W4391547476"],"abstract_inverted_index":{"Transformer-based":[0],"deep":[1],"learning":[2],"is":[3,35],"currently":[4],"the":[5,59,105,113,139,148,166],"state-of-the-art":[6],"in":[7,21,150],"many":[8],"NLP":[9],"and":[10,32,38,40,86,100,120],"IR":[11],"tasks.":[12],"However,":[13],"fine-tuning":[14],"such":[15],"Transformers":[16,99],"for":[17,63,76,160],"specific":[18],"tasks,":[19],"especially":[20],"scenarios":[22],"of":[23,26,54,107],"ever-expanding":[24],"volumes":[25],"data":[27],"with":[28,94,153],"constant":[29],"re-training":[30],"requirements":[31],"budget":[33],"constraints,":[34],"costly":[36],"(computationally":[37],"financially)":[39],"energy-consuming.":[41],"In":[42],"this":[43],"paper,":[44],"we":[45],"focus":[46,97],"on":[47,57,98,117,144],"Instance":[48],"Selection":[49],"(IS)":[50],"-":[51],"a":[52,91,95,131],"set":[53,115],"methods":[55],"focused":[56],"selecting":[58],"most":[60],"representative":[61],"documents":[62],"training,":[64],"aimed":[65],"at":[66],"maintaining":[67,147],"(or":[68,78],"improving)":[69],"classification":[70],"effectiveness":[71,149],"while":[72,146],"reducing":[73],"total":[74],"time":[75],"training":[77,114,140],"fine-tuning).":[79],"We":[80],"propose":[81],"E2SC-IS":[82,103,124],"--":[83,90],"Effective,":[84],"Efficient,":[85],"Scalable":[87],"Confidence-Based":[88],"IS":[89],"two-step":[92],"framework":[93],"particular":[96],"large":[101,162],"datasets.":[102],"estimates":[104],"probability":[106],"each":[108],"instance":[109],"being":[110],"removed":[111],"from":[112],"based":[116],"scalable,":[118],"fast,":[119],"calibrated":[121],"weak":[122],"classifiers.":[123],"also":[125],"exploits":[126],"iterative":[127],"heuristics":[128],"to":[129,157],"estimate":[130],"near-optimal":[132],"reduction":[133],"rate.":[134],"Our":[135],"solution":[136],"can":[137],"reduce":[138],"sets":[141],"by":[142],"29%":[143],"average":[145],"all":[151],"datasets,":[152],"speedup":[154],"gains":[155],"up":[156],"70%,":[158],"scaling":[159],"very":[161],"datasets":[163],"(something":[164],"that":[165],"baselines":[167],"cannot":[168],"do).":[169]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-18T07:39:51.176621","created_date":"2025-10-10T00:00:00"}