{"id":"https://openalex.org/W4401069835","doi":"https://doi.org/10.1109/access.2024.3435537","title":"Fine-Tuning of Distil-BERT for Continual Learning in Text Classification: An Experimental Analysis","display_name":"Fine-Tuning of Distil-BERT for Continual Learning in Text Classification: An Experimental Analysis","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4401069835","doi":"https://doi.org/10.1109/access.2024.3435537"},"language":"en","primary_location":{"id":"doi:10.1109/access.2024.3435537","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3435537","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2024.3435537","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049502092","display_name":"Sahar Shah","orcid":"https://orcid.org/0009-0001-5588-8823"},"institutions":[{"id":"https://openalex.org/I66752286","display_name":"University of Milano-Bicocca","ror":"https://ror.org/01ynf4891","country_code":"IT","type":"education","lineage":["https://openalex.org/I66752286"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Sahar Shah","raw_affiliation_strings":["Department of Informatics, Systems and Communication, University of Milano-Bicocca, Milan, Italy"],"raw_orcid":"https://orcid.org/0009-0001-5588-8823","affiliations":[{"raw_affiliation_string":"Department of Informatics, Systems and Communication, University of Milano-Bicocca, Milan, Italy","institution_ids":["https://openalex.org/I66752286"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102913859","display_name":"Sara Manzoni","orcid":"https://orcid.org/0000-0002-6406-536X"},"institutions":[{"id":"https://openalex.org/I66752286","display_name":"University of Milano-Bicocca","ror":"https://ror.org/01ynf4891","country_code":"IT","type":"education","lineage":["https://openalex.org/I66752286"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Sara Lucia Manzoni","raw_affiliation_strings":["Department of Informatics, Systems and Communication, University of Milano-Bicocca, Milan, Italy"],"raw_orcid":"https://orcid.org/0000-0002-6406-536X","affiliations":[{"raw_affiliation_string":"Department of Informatics, Systems and Communication, University of Milano-Bicocca, Milan, Italy","institution_ids":["https://openalex.org/I66752286"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068902908","display_name":"Farooq Zaman","orcid":"https://orcid.org/0000-0002-9861-4013"},"institutions":[{"id":"https://openalex.org/I1323252656","display_name":"Information Technology University","ror":"https://ror.org/00ngv8j44","country_code":"PK","type":"education","lineage":["https://openalex.org/I1323252656"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Farooq Zaman","raw_affiliation_strings":["Department of Computer Science, University of Information Technology, Lahore, Pakistan"],"raw_orcid":"https://orcid.org/0000-0002-9861-4013","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Information Technology, Lahore, Pakistan","institution_ids":["https://openalex.org/I1323252656"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106154011","display_name":"Fatima Es Sabery","orcid":null},"institutions":[{"id":"https://openalex.org/I99297268","display_name":"University of Hassan II Casablanca","ror":"https://ror.org/001q4kn48","country_code":"MA","type":"education","lineage":["https://openalex.org/I99297268"]}],"countries":["MA"],"is_corresponding":false,"raw_author_name":"Fatima Es Sabery","raw_affiliation_strings":["Department of Economics and Management Sciences, Faculty of Law, Economics and Social Sciences, Hassan II University of Casablanca, Mohammedia, Morocco"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Economics and Management Sciences, Faculty of Law, Economics and Social Sciences, Hassan II University of Casablanca, Mohammedia, Morocco","institution_ids":["https://openalex.org/I99297268"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062351659","display_name":"Francesco Epifania","orcid":"https://orcid.org/0000-0003-1839-9366"},"institutions":[{"id":"https://openalex.org/I4210138466","display_name":"Class Editori (Italy)","ror":"https://ror.org/040qe3166","country_code":"IT","type":"company","lineage":["https://openalex.org/I4210138466"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Francesco Epifania","raw_affiliation_strings":["Social Things srl, Milan, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Social Things srl, Milan, Italy","institution_ids":["https://openalex.org/I4210138466"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047943010","display_name":"Italo Zoppis","orcid":"https://orcid.org/0000-0001-7312-7123"},"institutions":[{"id":"https://openalex.org/I66752286","display_name":"University of Milano-Bicocca","ror":"https://ror.org/01ynf4891","country_code":"IT","type":"education","lineage":["https://openalex.org/I66752286"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Italo Francesco Zoppis","raw_affiliation_strings":["Department of Informatics, Systems and Communication, University of Milano-Bicocca, Milan, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics, Systems and Communication, University of Milano-Bicocca, Milan, Italy","institution_ids":["https://openalex.org/I66752286"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":3.3601,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.9314535,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"12","issue":null,"first_page":"104964","last_page":"104982"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9968000054359436,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9968000054359436,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9908999800682068,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9753000140190125,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/computer-science","display_name":"Computer science","score":0.8503360152244568},{"id":"https://openalex.org/keywords/forgetting","display_name":"Forgetting","score":0.6509841680526733},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6022639870643616},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5506349802017212},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5495582222938538},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5191116333007812},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.500939130783081},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4960196912288666},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4936622083187103},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.48032084107398987},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.4459449350833893},{"id":"https://openalex.org/keywords/f1-score","display_name":"F1 score","score":0.43610063195228577},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4184597134590149}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8503360152244568},{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.6509841680526733},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6022639870643616},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5506349802017212},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5495582222938538},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5191116333007812},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.500939130783081},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4960196912288666},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4936622083187103},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.48032084107398987},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.4459449350833893},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.43610063195228577},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4184597134590149},{"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/access.2024.3435537","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3435537","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:boa.unimib.it:10281/552954","is_oa":true,"landing_page_url":"https://hdl.handle.net/10281/552954","pdf_url":"https://boa.unimib.it/bitstream/10281/552954/2/Shah%20et%20al-2024-IEEE%20Access-VoR.pdf","source":{"id":"https://openalex.org/S4306401259","display_name":"BOA (University of Milano-Bicocca)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66752286","host_organization_name":"University of Milano-Bicocca","host_organization_lineage":["https://openalex.org/I66752286"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:doaj.org/article:7cbd432fe159472d8e395156567d20bf","is_oa":true,"landing_page_url":"https://doaj.org/article/7cbd432fe159472d8e395156567d20bf","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 12, Pp 104964-104982 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2024.3435537","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3435537","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.49000000953674316,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2747680751","https://openalex.org/W2788388592","https://openalex.org/W2794487997","https://openalex.org/W2898339904","https://openalex.org/W2973324789","https://openalex.org/W2991429427","https://openalex.org/W3020936289","https://openalex.org/W3100616641","https://openalex.org/W3119036516","https://openalex.org/W3155222352","https://openalex.org/W3171057731","https://openalex.org/W3172053684","https://openalex.org/W3196324893","https://openalex.org/W3199652424","https://openalex.org/W3209083906","https://openalex.org/W3212152676","https://openalex.org/W4205767597","https://openalex.org/W4210827551","https://openalex.org/W4225710862","https://openalex.org/W4229892888","https://openalex.org/W4281692210","https://openalex.org/W4283656590","https://openalex.org/W4289860408","https://openalex.org/W4293565917","https://openalex.org/W4307280064","https://openalex.org/W4318595446","https://openalex.org/W4327947795","https://openalex.org/W4377042032","https://openalex.org/W4378474100","https://openalex.org/W4380927922","https://openalex.org/W6770545627","https://openalex.org/W6801136434","https://openalex.org/W6853293300","https://openalex.org/W6890075866"],"related_works":["https://openalex.org/W4281760909","https://openalex.org/W2237537322","https://openalex.org/W2950678851","https://openalex.org/W4301248618","https://openalex.org/W2165343651","https://openalex.org/W2242427765","https://openalex.org/W2075830955","https://openalex.org/W2343790552","https://openalex.org/W3111398917","https://openalex.org/W4385507578"],"abstract_inverted_index":{"Continual":[0],"learning":[1,191,221,254,287,312,353,380],"(CL)":[2],"with":[3,138,311,370],"bidirectional":[4],"encoder":[5],"representation":[6,145],"from":[7],"transformer":[8],"(BERT)":[9],"and":[10,48,82,121,130,150,170,193,246,278,315,327,350,381],"its":[11,44],"variant":[12],"Distil-BERT,":[13],"have":[14],"shown":[15],"remarkable":[16],"performance":[17,107,177,362],"in":[18,64,108,181,366,373],"various":[19,367],"natural":[20],"language":[21],"processing":[22],"(NLP)":[23],"tasks,":[24,116,164,369],"such":[25],"as":[26],"text":[27],"classification":[28],"(TC).":[29],"However,":[30],"the":[31,60,72,101,128,143,197,200,203,226,253,259,262,268,286,292,322,330,352,360],"model":[32,73,91,186,188,205,230,334,365],"degrading":[33],"factors":[34],"like":[35],"catastrophic":[36],"forgetting":[37,78],"(CF),":[38],"accuracy,":[39,187],"task":[40,122],"dependent":[41],"architecture":[42,92],"ruined":[43],"popularity":[45],"for":[46],"complex":[47],"intelligent":[49],"tasks.":[50,66],"This":[51],"research":[52],"article":[53],"proposes":[54],"an":[55,207,232,297,336],"innovative":[56],"approach":[57],"to":[58,70,74,125,321,355],"address":[59],"challenges":[61],"of":[62,97,162,183,196,210,214,219,223,235,239,244,256,289,300,304,309,325,339,343,348,363,383],"CL":[63,109],"TC":[65,163,368],"The":[67,111,134,154,172],"objectives":[68],"are":[69],"enable":[71],"learn":[75],"continuously":[76],"without":[77],"previously":[79],"acquired":[80],"knowledge":[81],"perfectly":[83],"avoid":[84],"CF.":[85],"To":[86],"achieve":[87],"this,":[88],"a":[89,147,151],"task-independent":[90],"is":[93,157,271],"introduced,":[94],"allowing":[95],"training":[96,194,249,279,318,374],"multiple":[98,179],"tasks":[99,180],"on":[100,159],"same":[102],"model,":[103,136],"thereby":[104],"improving":[105],"overall":[106],"scenarios.":[110],"framework":[112],"incorporates":[113],"two":[114,139],"auxiliary":[115],"namely":[117],"next":[118],"sentence":[119],"prediction":[120],"identifier":[123],"prediction,":[124],"capture":[126],"both":[127],"task-generic":[129,148],"task-specific":[131,152],"contextual":[132],"information.":[133],"Distil-BERT":[135],"enhanced":[137],"linear":[140],"layers,":[141],"categorizes":[142],"output":[144],"into":[146],"space":[149],"space.":[153],"proposed":[155,204],"methodology":[156],"evaluated":[158],"diverse":[160],"sets":[161],"including":[165],"Yahoo,":[166],"Yelp,":[167],"Amazon,":[168],"DB-Pedia,":[169],"AG-News.":[171],"experimental":[173],"results":[174,358],"demonstrate":[175],"impressive":[176],"across":[178],"terms":[182],"F1":[184,208,233,263,298,337],"score,":[185],"evaluation":[189,217,242,274,307,346],"loss,":[190],"rate,":[192],"loss":[195,218,243,275,308,347],"model.":[198],"For":[199,258],"Yahoo":[201],"task,":[202,228,261,294,332],"achieved":[206,231,296],"score":[209,234,264,299,338],"96.84":[211],"%,":[212,216,237,241,267,273,302,306,341,345],"accuracy":[213,238,270,303,342],"95.85":[215],"0.06,":[220,245,277,349],"rate":[222,255,288,313,354],"0.00003144.":[224,290],"In":[225,291,329],"Yelp":[227],"our":[229,333,364],"96.66":[236],"97.66":[240],"similarly":[247],"minimized":[248,283,317],"losses":[250,280,319,375],"by":[251,284],"achieving":[252],"0.00003189.":[257],"Amazon":[260],"was":[265,276],"95.82":[266],"observed":[269],"97.83":[272],"were":[281],"effectively":[282],"securing":[285],"DB-Pedia":[293],"we":[295],"96.20":[301],"95.21":[305],"0.08,":[310],"0.0001972":[314],"rapidly":[316],"due":[320],"limited":[323],"number":[324],"epochs":[326],"instances.":[328],"AG-News":[331],"obtained":[335],"94.78":[340],"92.76":[344],"fixed":[351],"0.0001511.":[356],"These":[357],"highlight":[359],"exceptional":[361],"gradual":[371],"reduction":[372],"over":[376],"time,":[377],"indicating":[378],"effective":[379],"retention":[382],"knowledge.":[384]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}